mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-12 22:33:54 -04:00
feat(gallery): add Qwen3.8 Flash Next (#11763)
Add the Q4 and Q8 GGUF builds with the shared vision projector.\nThe variant pair lets LocalAI select the build that fits available memory.\n\nAssisted-by: Codex:gpt-5 Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
This commit is contained in:
localai-org-maint-botandlocalai-org-maint-bot authored and GitHub committed
1 parent
62f1c0ca7f
commit
16aa8ca004
1 file changed
+125
@@ -1,4 +1,129 @@
|
||||
---
|
||||
- &qwen3-8-flash-next
|
||||
name: "qwen3.8-flash-next-q4"
|
||||
variants:
|
||||
- model: qwen3.8-flash-next-q8
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
urls:
|
||||
- https://huggingface.co/Qwen/Qwen3.8-Flash-Next
|
||||
- https://huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF
|
||||
description: |
|
||||
Qwen3.8-Flash-Next is Qwen's 125B-parameter, 6B-active experimental
|
||||
vision-language mixture-of-experts model. It targets agentic coding,
|
||||
reasoning, tool use, and long-context workloads with a native 262K-token
|
||||
context window.
|
||||
|
||||
This default entry uses Unsloth's UD-Q4_K_XL GGUF and BF16 vision
|
||||
projector. The linked variant uses the higher-quality Q8_0 quantization.
|
||||
license: other
|
||||
tags:
|
||||
- llm
|
||||
- gguf
|
||||
- cpu
|
||||
- gpu
|
||||
- qwen
|
||||
- moe
|
||||
- reasoning
|
||||
- thinking
|
||||
- coding
|
||||
- agent
|
||||
- tools
|
||||
- vision
|
||||
- multimodal
|
||||
- long-context
|
||||
icon: https://qianwen-res.oss-cn-beijing.aliyuncs.com/logo_qwen.jpg
|
||||
last_checked: "2026-08-28"
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 262144
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- vision
|
||||
mmproj: llama-cpp/mmproj/qwen3.8-flash-next/mmproj-BF16.gguf
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
|
||||
presence_penalty: 0
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/UD-Q4_K_XL/Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
|
||||
sha256: 4448186216b3af4cc558bbce2c3213f01608f8f8b2e5267a9767971dd3ec8082
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-UD-Q4_K_XL-00002-of-00004.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/UD-Q4_K_XL/Qwen3.8-Flash-Next-UD-Q4_K_XL-00002-of-00004.gguf
|
||||
sha256: 3f342f1c1580473f1ee94ddd5b28206e8c07a70fa1a366f59d1d6c922919a6c9
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-UD-Q4_K_XL-00003-of-00004.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/UD-Q4_K_XL/Qwen3.8-Flash-Next-UD-Q4_K_XL-00003-of-00004.gguf
|
||||
sha256: 56758f40269cad5cd9b0d3d6fbae0f40f6d5be6de49e4ab392dbe83157d9cbd3
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-UD-Q4_K_XL-00004-of-00004.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/UD-Q4_K_XL/Qwen3.8-Flash-Next-UD-Q4_K_XL-00004-of-00004.gguf
|
||||
sha256: 753bda48b98ba4f1636134a90a967de1b2d3908a236c026e464777342e53510a
|
||||
- filename: llama-cpp/mmproj/qwen3.8-flash-next/mmproj-BF16.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/mmproj-BF16.gguf
|
||||
sha256: 2e788f8c511d8093c7b43cb87b2fd7e14228340318057f8fb20c86df2efe2355
|
||||
- !!merge <<: *qwen3-8-flash-next
|
||||
name: "qwen3.8-flash-next-q8"
|
||||
variants: []
|
||||
description: |
|
||||
Qwen3.8-Flash-Next in the higher-quality Q8_0 GGUF format, with the shared
|
||||
BF16 vision projector. This build preserves more model quality but needs
|
||||
more memory than the default Q4 variant.
|
||||
overrides:
|
||||
backend: llama-cpp
|
||||
context_size: 262144
|
||||
function:
|
||||
automatic_tool_parsing_fallback: true
|
||||
grammar:
|
||||
disable: true
|
||||
known_usecases:
|
||||
- chat
|
||||
- vision
|
||||
mmproj: llama-cpp/mmproj/qwen3.8-flash-next/mmproj-BF16.gguf
|
||||
options:
|
||||
- use_jinja:true
|
||||
parameters:
|
||||
min_p: 0
|
||||
model: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-Q8_0-00001-of-00006.gguf
|
||||
presence_penalty: 0
|
||||
repeat_penalty: 1
|
||||
temperature: 1
|
||||
top_k: 20
|
||||
top_p: 0.95
|
||||
template:
|
||||
use_tokenizer_template: true
|
||||
files:
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-Q8_0-00001-of-00006.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/Q8_0/Qwen3.8-Flash-Next-Q8_0-00001-of-00006.gguf
|
||||
sha256: 2dabcbb53ca537a7947bc7d20414fd464eeaf4d66d43021b5b2556cc87544ad2
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-Q8_0-00002-of-00006.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/Q8_0/Qwen3.8-Flash-Next-Q8_0-00002-of-00006.gguf
|
||||
sha256: 494ca4ed3dbf97bc28da88af3890b8877b9032f909812d00c0526a9ca5e91d2e
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-Q8_0-00003-of-00006.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/Q8_0/Qwen3.8-Flash-Next-Q8_0-00003-of-00006.gguf
|
||||
sha256: 34efd79a80a1ce540a517a5d56171924b66ce1c38b04c904f17ad6d8ef17cf20
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-Q8_0-00004-of-00006.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/Q8_0/Qwen3.8-Flash-Next-Q8_0-00004-of-00006.gguf
|
||||
sha256: bfa634025fabbd2658bf7694bc80b90e571699c768723f844c934c7ef06c691a
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-Q8_0-00005-of-00006.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/Q8_0/Qwen3.8-Flash-Next-Q8_0-00005-of-00006.gguf
|
||||
sha256: 232a8f14cc0fa4262e7efe8593774b136fe40909e39c7a020342ddaa27259a97
|
||||
- filename: llama-cpp/models/qwen3.8-flash-next/Qwen3.8-Flash-Next-Q8_0-00006-of-00006.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/Q8_0/Qwen3.8-Flash-Next-Q8_0-00006-of-00006.gguf
|
||||
sha256: 538a93bca918064983409a41187ad4c68640f9aced6f29564da8f551bf86d7a5
|
||||
- filename: llama-cpp/mmproj/qwen3.8-flash-next/mmproj-BF16.gguf
|
||||
uri: huggingface://unsloth/Qwen3.8-Flash-Next-GGUF/mmproj-BF16.gguf
|
||||
sha256: 2e788f8c511d8093c7b43cb87b2fd7e14228340318057f8fb20c86df2efe2355
|
||||
- &granite-4-2-3b
|
||||
name: "granite-4.2-3b-q4"
|
||||
variants:
|
||||
|
||||
Reference in new issue
Block a user