Medina-Qwen3.5-27B-OpenClaw-uncensored โ€” GGUF

GGUF quantizations of Y0us/Medina-Qwen3.5-27B-OpenClaw-uncensored, an abliterated variant of peterjohannmedina/Medina-Qwen3.5-27B-OpenClaw.

For full methodology and evaluation details, see the main model card.


GGUF Downloads

Quantization Size Use case
F16 51 GB Reference / re-quantization source
Q4_K_M 16 GB โœ… Recommended โ€” 24 GB VRAM or 32 GB unified memory

Abliteration Summary

Parameter Value
Base Medina-Qwen3.5-27B-OpenClaw (base + LoRA merged to BF16)
Method Refusal-direction projection
Target weights attention o_proj, linear-attention out_proj, MLP down_proj
Layers modified 40 (top by refusal contribution)
Refusal scope English + Korean patterns

Evaluation

Numbers below are from the Q4_K_M build in this repo. All runs used llama.cpp with --parallel 1 --cache-reuse 0, temperature=0.0, greedy decoding.

Refusal rate (mlabonne/harmful_behaviors, N=50)

Model Refusals Rate
Original Medina-Qwen3.5-27B-OpenClaw 50 / 50 100.0%
This model 0 / 50 0.0%

Capability preservation

Benchmark Original Uncensored ฮ”
MMLU High School Computer Science 93.33% 96.67% +3.33
MMLU College Mathematics 93.33% 93.33% 0.00
MMLU Formal Logic 96.67% 96.67% 0.00
MMLU Professional Law 83.33% 76.67% โˆ’6.67
MMLU Moral Scenarios 73.33% 76.67% +3.33
MMLU Overall (150 Q) 88.00% 88.00% 0.00
GSM8K (50 Q) 98.00% 98.00% 0.00

MMLU and GSM8K run 0-shot in generation mode (CoT + Answer: X). Overall MMLU and GSM8K are identical (132/150 and 49/50).


Usage with llama.cpp

./llama-server \
  -m Medina-Qwen3.5-27B-OpenClaw-uncensored-Q4_K_M.gguf \
  --port 8080 --host 127.0.0.1 \
  -c 8192 -ngl 999 \
  --chat-template chatml \
  --parallel 1 \
  --cache-reuse 0

Important flags for this architecture:

  • --parallel 1 โ€” the base uses hybrid GatedDeltaNet + attention; parallel slots thrash the cache.
  • --cache-reuse 0 โ€” KV cache cannot currently be reused across turns for this architecture under llama.cpp.

See llama.cpp PR #13194 for background.

Usage with Ollama

# Direct from this repo (after quantization is hosted)
ollama run hf.co/Y0us/Medina-Qwen3.5-27B-OpenClaw-uncensored-GGUF:Q4_K_M

Known Limitations

  • Hybrid architecture prevents KV-cache reuse across turns under current llama.cpp โ€” every prompt is fully re-processed (runtime limitation, not a weight issue).
  • Refusal benchmark (N=50) is a sanity check, not an exhaustive safety audit.
  • Professional Law shows a โˆ’6.67 point drop on MMLU (N=30).

License

Apache 2.0 โ€” same as the base model.

Downloads last month
65
GGUF
Model size
27B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

4-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Y0us/Medina-Qwen3.5-27B-OpenClaw-Uncensored-GGUF