From 622ac48d0f35f73171fc0f788a490c44bd4416ee Mon Sep 17 00:00:00 2001 From: Dorian Magasic Date: Mon, 26 Oct 2026 18:23:53 +0000 Subject: [PATCH] feat(gallery): add Qwen3.5 Artemis 2B, 4B and 9B variants Add eight TurinTech Artemis GGUF builds of Qwen3.5 2B, 4B and 9B, each with the repo's F16 vision projector, pinned by revision and SHA-256. Assisted-by: Claude:claude-opus-5-5 Signed-off-by: Dorian Magasic --- gallery/index.yaml | 346 ++++++++++++++++++++++++++++++++ gallery/models/index.yaml | 410 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 756 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index b3d4cc2183..c1896242e6 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1464,6 +1464,352 @@ model: Qwen3.5-0.8B-Artemis-Q4_K_M.gguf template: use_tokenizer_template: true +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-2b-artemis-q5-k-m + description: | + TurinTech Artemis Q5_K_M quantization of Qwen3.5 2B for local tool calls, + maths, and instruction following. Accepts image input through the + bundled F16 vision projector. Uses the embedded chat template and an + 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-2B + - https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q5_K_M.gguf + sha256: 00643c030243fd097ea7e3b3877f06c740562b4ed066964b2cd6d13c23c9820d + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/Qwen3.5-2B-Artemis-Q5_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + sha256: ecbea1bda7d4bedb3851cf47f440ba5f8207a5943c6336aa482994825cf0d16f + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q5_K_M.gguf + template: + use_tokenizer_template: true + variants: + - model: qwen3.5-2b-artemis-q4-k-m +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-2b-artemis-q4-k-m + description: | + TurinTech Artemis Q4_K_M quantization of Qwen3.5 2B for local tool calls, + maths, and instruction following. Accepts image input through the + bundled F16 vision projector. Uses the embedded chat template and an + 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-2B + - https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q4_K_M.gguf + sha256: 86134884b896fdf3072c75a1028aa68361463e133be34b59453bcf4841205636 + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/Qwen3.5-2B-Artemis-Q4_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + sha256: ecbea1bda7d4bedb3851cf47f440ba5f8207a5943c6336aa482994825cf0d16f + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q4_K_M.gguf + template: + use_tokenizer_template: true +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-4b-artemis-q4-k-m + description: | + TurinTech Artemis Q4_K_M quantization of Qwen3.5 4B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-4B + - https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q4_K_M.gguf + sha256: 9cc4043170052b9f99e56974ec0c5c63fbae36e562da031baea3658ad6348b05 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/Qwen3.5-4B-Artemis-Q4_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + sha256: 0583309597e4c5b7fd206f050d3e208322ba7216ee7a57186692a10653a139f7 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q4_K_M.gguf + template: + use_tokenizer_template: true + variants: + - model: qwen3.5-4b-artemis-q5-k-m + - model: qwen3.5-4b-artemis-q5-k-s +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-4b-artemis-q5-k-m + description: | + TurinTech Artemis Q5_K_M quantization of Qwen3.5 4B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-4B + - https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_M.gguf + sha256: 930f7c1df65b2ee37a9af74698e695eea99c60429ed322d374f889988f9edd6d + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/Qwen3.5-4B-Artemis-Q5_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + sha256: 0583309597e4c5b7fd206f050d3e208322ba7216ee7a57186692a10653a139f7 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_M.gguf + template: + use_tokenizer_template: true +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-4b-artemis-q5-k-s + description: | + TurinTech Artemis Q5_K_S quantization of Qwen3.5 4B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-4B + - https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_S.gguf + sha256: a3ad5db0ad10c3e41f36d8fd8803dff7727f7ca575acb1421cbdc5558bf705f1 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/Qwen3.5-4B-Artemis-Q5_K_S.gguf + - filename: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + sha256: 0583309597e4c5b7fd206f050d3e208322ba7216ee7a57186692a10653a139f7 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_S.gguf + template: + use_tokenizer_template: true +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-9b-artemis-q4-k-m + description: | + TurinTech Artemis Q4_K_M quantization of Qwen3.5 9B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-9B + - https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q4_K_M.gguf + sha256: afa19e164e16f3496d4bbf85b2129e6d98102f6c41e8dc1e8bcda1f6b2234665 + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/Qwen3.5-9B-Artemis-Q4_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + sha256: 67716b06c20a75f68f8d0057ed3718cd967bdd1f594df7ee057f4001299c6eae + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q4_K_M.gguf + template: + use_tokenizer_template: true + variants: + - model: qwen3.5-9b-artemis-q5-k-s + - model: qwen3.5-9b-artemis-iq4-xs +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-9b-artemis-q5-k-s + description: | + TurinTech Artemis Q5_K_S quantization of Qwen3.5 9B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-9B + - https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q5_K_S.gguf + sha256: c223fbf19c51805832e7bbb92537d17cfa70a26cdb4b816743ff311957264a06 + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/Qwen3.5-9B-Artemis-Q5_K_S.gguf + - filename: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + sha256: 67716b06c20a75f68f8d0057ed3718cd967bdd1f594df7ee057f4001299c6eae + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q5_K_S.gguf + template: + use_tokenizer_template: true +- url: github:mudler/LocalAI/gallery/virtual.yaml@master + name: qwen3.5-9b-artemis-iq4-xs + description: | + TurinTech Artemis IQ4_XS quantization of Qwen3.5 9B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-9B + - https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF + icon: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/assets/turintech-logo.png + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + files: + - filename: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-IQ4_XS.gguf + sha256: ccf73846d6c4fcfc0b947d25365dd6c5c8c9d9b436b5ad97903b9cceb3d6a242 + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/Qwen3.5-9B-Artemis-IQ4_XS.gguf + - filename: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + sha256: 67716b06c20a75f68f8d0057ed3718cd967bdd1f594df7ee057f4001299c6eae + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-IQ4_XS.gguf + template: + use_tokenizer_template: true - url: github:mudler/LocalAI/gallery/virtual.yaml@master name: diplodocus-preview-q4 description: | diff --git a/gallery/models/index.yaml b/gallery/models/index.yaml index 000476beb1..fc85be05a4 100644 --- a/gallery/models/index.yaml +++ b/gallery/models/index.yaml @@ -1753,6 +1753,416 @@ model: Qwen3.5-0.8B-Artemis-Q4_K_M.gguf template: use_tokenizer_template: true +- kind: model + id: qwen3.5-2b-artemis-q5-k-m + name: qwen3.5-2b-artemis-q5-k-m + version: 0.0.0-gallery.3673445d9d44 + description: | + TurinTech Artemis Q5_K_M quantization of Qwen3.5 2B for local tool calls, + maths, and instruction following. Accepts image input through the + bundled F16 vision projector. Uses the embedded chat template and an + 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-2B + - https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q5_K_M.gguf + sha256: 00643c030243fd097ea7e3b3877f06c740562b4ed066964b2cd6d13c23c9820d + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/Qwen3.5-2B-Artemis-Q5_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + sha256: ecbea1bda7d4bedb3851cf47f440ba5f8207a5943c6336aa482994825cf0d16f + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q5_K_M.gguf + template: + use_tokenizer_template: true + variants: + - model: qwen3.5-2b-artemis-q4-k-m +- kind: model + id: qwen3.5-2b-artemis-q4-k-m + name: qwen3.5-2b-artemis-q4-k-m + version: 0.0.0-gallery.2c0309a89ccc + description: | + TurinTech Artemis Q4_K_M quantization of Qwen3.5 2B for local tool calls, + maths, and instruction following. Accepts image input through the + bundled F16 vision projector. Uses the embedded chat template and an + 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-2B + - https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q4_K_M.gguf + sha256: 86134884b896fdf3072c75a1028aa68361463e133be34b59453bcf4841205636 + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/Qwen3.5-2B-Artemis-Q4_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + sha256: ecbea1bda7d4bedb3851cf47f440ba5f8207a5943c6336aa482994825cf0d16f + uri: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF/resolve/ef505832b8853db0c7b019f8ac6078d3a7289682/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-2B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-2B-Artemis-GGUF/Qwen3.5-2B-Artemis-Q4_K_M.gguf + template: + use_tokenizer_template: true +- kind: model + id: qwen3.5-4b-artemis-q4-k-m + name: qwen3.5-4b-artemis-q4-k-m + version: 0.0.0-gallery.76b49963e0c0 + description: | + TurinTech Artemis Q4_K_M quantization of Qwen3.5 4B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-4B + - https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q4_K_M.gguf + sha256: 9cc4043170052b9f99e56974ec0c5c63fbae36e562da031baea3658ad6348b05 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/Qwen3.5-4B-Artemis-Q4_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + sha256: 0583309597e4c5b7fd206f050d3e208322ba7216ee7a57186692a10653a139f7 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q4_K_M.gguf + template: + use_tokenizer_template: true + variants: + - model: qwen3.5-4b-artemis-q5-k-m + - model: qwen3.5-4b-artemis-q5-k-s +- kind: model + id: qwen3.5-4b-artemis-q5-k-m + name: qwen3.5-4b-artemis-q5-k-m + version: 0.0.0-gallery.42232fb9450e + description: | + TurinTech Artemis Q5_K_M quantization of Qwen3.5 4B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-4B + - https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_M.gguf + sha256: 930f7c1df65b2ee37a9af74698e695eea99c60429ed322d374f889988f9edd6d + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/Qwen3.5-4B-Artemis-Q5_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + sha256: 0583309597e4c5b7fd206f050d3e208322ba7216ee7a57186692a10653a139f7 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_M.gguf + template: + use_tokenizer_template: true +- kind: model + id: qwen3.5-4b-artemis-q5-k-s + name: qwen3.5-4b-artemis-q5-k-s + version: 0.0.0-gallery.6b546b2f6c7b + description: | + TurinTech Artemis Q5_K_S quantization of Qwen3.5 4B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-4B + - https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_S.gguf + sha256: a3ad5db0ad10c3e41f36d8fd8803dff7727f7ca575acb1421cbdc5558bf705f1 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/Qwen3.5-4B-Artemis-Q5_K_S.gguf + - filename: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + sha256: 0583309597e4c5b7fd206f050d3e208322ba7216ee7a57186692a10653a139f7 + uri: https://huggingface.co/turintech/Qwen3.5-4B-Artemis-GGUF/resolve/ae130c914b6d3eea3653b16d14dea5f0a4508518/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-4B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-4B-Artemis-GGUF/Qwen3.5-4B-Artemis-Q5_K_S.gguf + template: + use_tokenizer_template: true +- kind: model + id: qwen3.5-9b-artemis-q4-k-m + name: qwen3.5-9b-artemis-q4-k-m + version: 0.0.0-gallery.834797c59c23 + description: | + TurinTech Artemis Q4_K_M quantization of Qwen3.5 9B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-9B + - https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q4_K_M.gguf + sha256: afa19e164e16f3496d4bbf85b2129e6d98102f6c41e8dc1e8bcda1f6b2234665 + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/Qwen3.5-9B-Artemis-Q4_K_M.gguf + - filename: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + sha256: 67716b06c20a75f68f8d0057ed3718cd967bdd1f594df7ee057f4001299c6eae + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q4_K_M.gguf + template: + use_tokenizer_template: true + variants: + - model: qwen3.5-9b-artemis-q5-k-s + - model: qwen3.5-9b-artemis-iq4-xs +- kind: model + id: qwen3.5-9b-artemis-q5-k-s + name: qwen3.5-9b-artemis-q5-k-s + version: 0.0.0-gallery.0961936ab210 + description: | + TurinTech Artemis Q5_K_S quantization of Qwen3.5 9B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-9B + - https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q5_K_S.gguf + sha256: c223fbf19c51805832e7bbb92537d17cfa70a26cdb4b816743ff311957264a06 + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/Qwen3.5-9B-Artemis-Q5_K_S.gguf + - filename: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + sha256: 67716b06c20a75f68f8d0057ed3718cd967bdd1f594df7ee057f4001299c6eae + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-Q5_K_S.gguf + template: + use_tokenizer_template: true +- kind: model + id: qwen3.5-9b-artemis-iq4-xs + name: qwen3.5-9b-artemis-iq4-xs + version: 0.0.0-gallery.7e46815e604f + description: | + TurinTech Artemis IQ4_XS quantization of Qwen3.5 9B for local chat and + tool calls. Accepts image input through the bundled F16 vision + projector. Uses the embedded chat template and an 8192-token context. + license: apache-2.0 + urls: + - https://huggingface.co/Qwen/Qwen3.5-9B + - https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - multimodal + - vision + icon: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/assets/turintech-logo.png + channel: gallery + policy: + requireSignature: false + schemaVersion: 1 + model: + url: github:mudler/LocalAI/gallery/virtual.yaml@master + files: + - filename: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-IQ4_XS.gguf + sha256: ccf73846d6c4fcfc0b947d25365dd6c5c8c9d9b436b5ad97903b9cceb3d6a242 + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/Qwen3.5-9B-Artemis-IQ4_XS.gguf + - filename: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + sha256: 67716b06c20a75f68f8d0057ed3718cd967bdd1f594df7ee057f4001299c6eae + uri: https://huggingface.co/turintech/Qwen3.5-9B-Artemis-GGUF/resolve/258b5d4e90972c74423a22f380906a3a939a758a/mmproj-F16.gguf + overrides: + backend: llama-cpp + context_size: 8192 + function: + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.5-9B-Artemis-GGUF/mmproj-F16.gguf + options: + - use_jinja:true + parameters: + model: llama-cpp/models/Qwen3.5-9B-Artemis-GGUF/Qwen3.5-9B-Artemis-IQ4_XS.gguf + template: + use_tokenizer_template: true - kind: model id: diplodocus-preview-q4 name: diplodocus-preview-q4