mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-10-28 17:18:49 -04:00
Code Issues Packages Projects Releases Wiki Activity

chore(gallery): add Fable 5 Coding variants

Browse Source 
Add Q4_K_M and Q8_0 builds with the F16 vision projector for llama.cpp.
Pin downloads, verify SHA256 values, and document variant selection.

Assisted-by: Codex:gpt-6

(cherry picked from commit 19c30fd2ef, mudler/LocalAI#12630)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
localai-org-maint-bot authored and Ettore Di Giacinto committed 2026-10-13 07:30:41 +00:00
1 parent ae013099ca
commit bd5c2eebae
1 file changed
+88
Download Patch File Download Diff File Expand all files Collapse all files
gallery/index.yaml
+88
View File
@@ -937,6 +937,94 @@
- filename: mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf
sha256: ff348f3180a63188aa7285db85f550fe38acb61dd013c599eb8bad08d2cc2576
uri: https://huggingface.co/bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF/resolve/4371da10c84fb26da3592d4cf312d24aa82b7b65/mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf
- name: qwen3.8-27b-fable-5-coding-distilled
variants:
- model: qwen3.8-27b-fable-5-coding-distilled-q8
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls:
- https://huggingface.co/khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled
- https://huggingface.co/mradermacher/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF
description: |
A 27B Qwen3.8 fine-tune for coding, debugging, and agentic reasoning.
This Q4_K_M GGUF build uses llama.cpp, the embedded chat template, and the F16 vision projector.
license: apache-2.0
tags:
- llm
- gguf
- cpu
- gpu
- coding
- reasoning
- vision
- multimodal
last_checked: "2026-10-11"
overrides:
backend: llama-cpp
context_size: 32768
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- vision
mmproj: Qwen3.8-27B-Fable-5-Coding-Distilled.mmproj-f16.gguf
options:
- use_jinja:true
template:
use_tokenizer_template: true
parameters:
model: Qwen3.8-27B-Fable-5-Coding-Distilled.Q4_K_M.gguf
files:
- filename: Qwen3.8-27B-Fable-5-Coding-Distilled.Q4_K_M.gguf
sha256: f730bb8dd54fc9ae404d5fbe65fe2cbde54d099ac76214a87641c70328dc6c5c
uri: https://huggingface.co/mradermacher/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF/resolve/e8eeb91df17f4b8c107dbaaf3edeeff9f9bfb928/Qwen3.8-27B-Fable-5-Coding-Distilled.Q4_K_M.gguf
- filename: Qwen3.8-27B-Fable-5-Coding-Distilled.mmproj-f16.gguf
sha256: 5311f1ec862e2e3745f1ba89a958ceea754d048ca883baf5b11a8333d2e5f060
uri: https://huggingface.co/mradermacher/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF/resolve/e8eeb91df17f4b8c107dbaaf3edeeff9f9bfb928/Qwen3.8-27B-Fable-5-Coding-Distilled.mmproj-f16.gguf
- name: qwen3.8-27b-fable-5-coding-distilled-q8
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls:
- https://huggingface.co/khazarai/Qwen3.8-27B-Fable-5-Coding-Distilled
- https://huggingface.co/mradermacher/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF
description: |
A 27B Qwen3.8 fine-tune for coding, debugging, and agentic reasoning.
This Q8_0 GGUF build uses llama.cpp, the embedded chat template, and the F16 vision projector.
license: apache-2.0
tags:
- llm
- gguf
- cpu
- gpu
- coding
- reasoning
- vision
- multimodal
last_checked: "2026-10-11"
overrides:
backend: llama-cpp
context_size: 32768
function:
automatic_tool_parsing_fallback: true
grammar:
disable: true
known_usecases:
- chat
- vision
mmproj: Qwen3.8-27B-Fable-5-Coding-Distilled.mmproj-f16.gguf
options:
- use_jinja:true
template:
use_tokenizer_template: true
parameters:
model: Qwen3.8-27B-Fable-5-Coding-Distilled.Q8_0.gguf
files:
- filename: Qwen3.8-27B-Fable-5-Coding-Distilled.Q8_0.gguf
sha256: 07896593624778f6a0912bd2553ff17332d7bd169c818e8ff8413abdd931a842
uri: https://huggingface.co/mradermacher/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF/resolve/e8eeb91df17f4b8c107dbaaf3edeeff9f9bfb928/Qwen3.8-27B-Fable-5-Coding-Distilled.Q8_0.gguf
- filename: Qwen3.8-27B-Fable-5-Coding-Distilled.mmproj-f16.gguf
sha256: 5311f1ec862e2e3745f1ba89a958ceea754d048ca883baf5b11a8333d2e5f060
uri: https://huggingface.co/mradermacher/Qwen3.8-27B-Fable-5-Coding-Distilled-GGUF/resolve/e8eeb91df17f4b8c107dbaaf3edeeff9f9bfb928/Qwen3.8-27B-Fable-5-Coding-Distilled.mmproj-f16.gguf
- name: thinkingcap-qwen3.8-27b
variants:
- model: thinkingcap-qwen3.8-27b-q8