Model Intelligence Sheet
schneewolflabs/B1-27B-GGUF overview
B1 27B GGUF Q8 0 quant of schneewolflabs/B1 27B https://huggingface.co/schneewolflabs/B1 27B plus the vision mmproj f16, byte identical to B0 27B's . MTP tenso…
Runs locally from ~884.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | schneewolflabs/B1-27B-GGUF |
|---|---|
| Author | schneewolflabs |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | schneewolflabs/B1-27B |
| Last modified | 2026-09-07T18:21:52.000Z |
Model README
---
base_model:
- schneewolflabs/B1-27B
license: apache-2.0
pipeline_tag: image-text-to-text
tags:
- gguf
- agents
- tool-use
- reasoning
- qwen3.8
---
B1-27B GGUF
Q8_0 quant of schneewolflabs/B1-27B
plus the vision mmproj (f16, byte-identical to B0-27B's). MTP tensors intact —
--spec-type draft-mtp works.
llama-server -m B1-27B-Q8_0.gguf --mmproj B1-27B-mmproj-f16.gguf \
-ngl 99 -c 16384 --jinja -fa on -np 1 \
--spec-type draft-mtp --spec-draft-n-max 4Run schneewolflabs/B1-27B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models