Aller au contenu
ModelPrésentéExterne
Browse files

Legal Qwen3.6 27B Abliterated GGUF

GGUF build of Legal-Qwen3.6-27B-Abliterated for Ollama / llama.cpp.

Sourcehuggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF/tree/6b8aea0054d50583f569283c3e1fdd495899e345
TypeOtherModèle de basescottyjmp5/Legal-Qwen3.6-27B-AbliteratedVersionRevision 6b8aea0UnratedClasse

Source du modèle

Type
Other
Taille du fichier
888 MB–15,7 GB
Modèle de base
scottyjmp5/Legal-Qwen3.6-27B-Abliterated
Version
vRevision 6b8aea0
Mis à jour
5 nov. 2026
Téléchargements
88
Source
Hugging Face

Description de la source

Legal-Qwen3.6-27B-Abliterated-GGUF

GGUF build of Legal-Qwen3.6-27B-Abliterated for Ollama / llama.cpp.

FileSizeNotes
legal-27b.Q4_K_M.gguf16 GBtext model, Q4_K_M
legal-27b-mmproj.gguf0.9 GBvision projector (required for image input)

Runs fully on a single 24-32 GB GPU. Verified on an RTX 5090 at ~71 tok/s with vision, tool calling, and thinking all working through Ollama 0.32+.

Ollama

# Modelfile
FROM ./legal-27b.Q4_K_M.gguf
FROM ./legal-27b-mmproj.gguf
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95

ollama create legal-27b -f Modelfile
ollama run legal-27b

The RENDERER/PARSER qwen3.5 lines matter: they enable Ollama's built-in chat template and tool-call/thinking parsing for the Qwen3.5/3.6 family.

See the main model card for training details, the retrieval (RAG) recommendation, and warnings (abliterated base; not legal advice).

Sources

1 source
Hugging FacePrincipalVersion 6b8aea0054d50583f569283c3e1fdd495899e345
huggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF/tree/6b8aea0054d50583f569283c3e1fdd495899e345

Vérifié 5 nov.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

2 artefacts

legal-27b-mmproj.gguf

gguf · 888 MB · SHA-256 6b846fb292dc…3c37 · Hugging Face

Download file

legal-27b.Q4_K_M.gguf

gguf · Q4_K_M (unverified) · 15,7 GB · SHA-256 e069c88c6bd3…fe7e · Hugging Face

Download file

Extraits de sources

3 extraits
Readme28 aoûthuggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF

--- license: apache-2.0 base_model: scottyjmp5/Legal-Qwen3.6-27B-Abliterated datasets: - scottyjmp5/courtlistener-legal-corpus language: - en pipeline_tag: image-text-to-text tags: - legal - caselaw - abliterated - vision - tool-calling - gguf - ollama - llama.cpp --- # Legal-Qwen3.6-27B-Abliterated-GGUF GGUF build of [Legal-Qwen3.6-27B-Abliterated](https://huggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated) for Ollama / llama.cpp. | File | Size | Notes | |---|---|---| | `legal-27b.Q4_K_M.gguf` | 16 GB | text model, Q4_K_M | | `legal-27b-mmproj.gguf` | 0.9 GB | vision projector (required for image input) | Runs fully on a single 24-32 GB GPU. Verified on an RTX 5090 at ~71 tok/s with vision, tool calling, and thinking all working through Ollama 0.32+. ## Ollama ``` # Modelfile FROM ./legal-27b.Q4_K_M.gguf FROM ./legal-27b-mmproj.gguf RENDERER qwen3.5 PARSER qwen3.5 PARAMETER temperature 1 PARAMETER top_k 20 PARAMETER top_p 0.95 ollama create legal-27b -f Modelfile ollama run legal-27b ``` The `RENDERER`/`PARSER qwen3.5` lines matter: they enable Ollama's built-in chat template and tool-call/thinking parsing for the Qwen3.5/3.6 family. See the [main model card](https://huggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated) for training details, the retrieval (RAG) recommendation, and warnings (abliterated base; not legal advice).

Note5 nov.huggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF

Source context: 88 downloads · 0 likes · Pipeline image-text-to-text · Repo scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF

Note28 aoûthuggingface.co/scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF

Source context: 87 downloads · 0 likes · Pipeline image-text-to-text · Repo scottyjmp5/Legal-Qwen3.6-27B-Abliterated-GGUF