diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index b8cf63898..7a659919d 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -233,6 +233,13 @@ whole page has variants. curl http://localhost:8080/api/models | jq '.models[] | select(.has_variants) | .name' ``` +The Tiel-Coder gallery entry offers Q4, Q5, Q6, and Q8 MTP builds for +llama.cpp, each with the BF16 vision projector. To select the Q6 MTP build: + +```bash +local-ai models install tiel-coder-35b-a3b-q4 --variant tiel-coder-35b-a3b-q6-mtp +``` + ### Collapsing the listing to one row per model By default the listing returns every entry, including the individual builds a diff --git a/gallery/index.yaml b/gallery/index.yaml index 804049539..0049dadac 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2415,6 +2415,9 @@ name: "tiel-coder-35b-a3b-q4" variants: - model: tiel-coder-35b-a3b-q4-mtp + - model: tiel-coder-35b-a3b-q5-mtp + - model: tiel-coder-35b-a3b-q6-mtp + - model: tiel-coder-35b-a3b-q8-mtp - model: tiel-coder-35b-a3b-q8 url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: @@ -2515,6 +2518,159 @@ - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf uri: huggingface://peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/mmproj-BF16.gguf sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 +- !!merge <<: *tiel-coder-35b-a3b + name: "tiel-coder-35b-a3b-q5-mtp" + variants: [] + last_checked: "2026-09-09" + urls: + - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B + - https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Tiel-Coder-35B-A3B in Q5_K_XL format with MTP speculative decoding and a + BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - reasoning + - thinking + - coding + - agent + - tools + - vision + - multimodal + - long-context + - mtp + overrides: + backend: llama-cpp + context_size: 262144 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q5_K_XL.gguf + sha256: 83278fd1ea9923edb45cf6d373a8aa6475fb1f855795e085b9e6252bc53f24fa + - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 +- !!merge <<: *tiel-coder-35b-a3b + name: "tiel-coder-35b-a3b-q6-mtp" + variants: [] + last_checked: "2026-09-09" + urls: + - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B + - https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Tiel-Coder-35B-A3B in Q6_K_XL format with MTP speculative decoding and a + BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - reasoning + - thinking + - coding + - agent + - tools + - vision + - multimodal + - long-context + - mtp + overrides: + backend: llama-cpp + context_size: 262144 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf + sha256: a13a71ecfd00779fa3e0071674da61afbdffd42050f22173f4142989975573ba + - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 +- !!merge <<: *tiel-coder-35b-a3b + name: "tiel-coder-35b-a3b-q8-mtp" + variants: [] + last_checked: "2026-09-09" + urls: + - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B + - https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP + description: | + Tiel-Coder-35B-A3B in Q8_K_XL format with MTP speculative decoding and a + BF16 vision projector. + tags: + - llm + - gguf + - cpu + - gpu + - qwen + - moe + - reasoning + - thinking + - coding + - agent + - tools + - vision + - multimodal + - long-context + - mtp + overrides: + backend: llama-cpp + context_size: 262144 + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + parameters: + model: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/tiel-coder-35b-a3b-mtp/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/Tiel-Coder-35B-A3B-MTP-UD-Q8_K_XL.gguf + sha256: 8384abe448e6159b1d43249be9c51f68fe5771e962bb39e3ee89ad1215385310 + - filename: llama-cpp/mmproj/tiel-coder-35b-a3b-mtp/mmproj-BF16.gguf + uri: https://huggingface.co/peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP/resolve/182ae2b61f15ca133f160c6e11badc2791b052fd/mmproj-BF16.gguf + sha256: d9ce31026d1cb1f3f8d5152e2e2a014d9d2b302b6c93a7dc07bb0a0487f52837 - !!merge <<: *tiel-coder-35b-a3b name: "tiel-coder-35b-a3b-q8" variants: []