Sign up

Shiftedx/Qwen3.8-27B-Abliterated-MLX-MXFP4-MTP

🤗 Hugging Face sourceimage-text-to-textapache-2.027.4B params55 GBsafetensors✓ HF checksums availableupdated today
No torrent yet →

Qwen3.8-27B Abliterated MLX MXFP4 + Native MTP

Vision-enabled MTPLX package of Qwen/Qwen3.8-27B, pinned to revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0, with a measured refusal-direction edit.

  • Language model: MXFP4, group size 32; strength 2.5 norm-preserving edit on 128 modules
  • Vision tower: unchanged same-revision BF16 weights
  • Speculation: 15 unchanged native BF16 MTP tensors; recommended depth 3
  • Runtime: MTPLX 2.0.2 or newer

The frozen held-out behavior suite changed measured refusal markers from 12/12 to 0/12, with benign-sensitive refusal at 0/12 and utility at 6/6. MTPLX tensor inspection, text generation, and three vision requests through its API passed. This is scoped evidence, not a claim that the model is universally “uncensored.”

The Hub's approximately 5.5B safetensors count reflects packed MXFP storage elements; the underlying architecture remains the full 27B model.

mtplx quickstart \
  --model Shiftedx/Qwen3.8-27B-Abliterated-MLX-MXFP4-MTP \
  --mtp --depth 3 --profile sustained

This edit reduces refusal behavior and may increase harmful or incorrect outputs. Treat prompts, images, and outputs as untrusted; do not submit secrets, and sandbox tools or generated code with least-privilege access. This package adds no telemetry or remote execution.

The upstream Apache-2.0 license and model limitations continue to apply.

Shiftedx Bench post-publication qualification

This table was generated from the frozen lightweight quant gate after the model weights were published. Categories remain separate; the benchmark does not produce a composite intelligence score.

Lane Passed Accuracy Mean wall time Mean decode Peak active memory
Quality 6/10 60.0% 22.41 s 53.46 tok/s 32.36 GiB
Long context 13/15 86.7% 145.65 s 42.63 tok/s 41.02 GiB
Tool calling 6/6 100.0% 4.26 s 41.08 tok/s 35.18 GiB
Agentic 0/2 0.0% 19.22 s — tok/s —
Vision 3/4 75.0% 4.81 s 49.61 tok/s 34.42 GiB
  • Tested model revision: d6352f90f36268551b9032b37ec92fe89c1a4ebe
  • Benchmark: Shiftedx Bench v0.3.0
  • Context lengths represented: 4,096, 16,384, 65,536, 131,072 prompt tokens; effective tested context: 131,072 tokens
  • Runtime contract: MTPLX 2.7.1 sustained; thinking on/medium; sampler temperature=1.0, top_p=0.95, top_k=20; Hermes hybrid routing with native explicit-parallel calls; KV cache off; MTP depth 3
  • Host: Apple M4 Max, 64 GiB unified memory
  • Total measured request wall time: 2492.15 seconds
  • 260,096-token status: not run; it is outside the lightweight quant gate.

Scores are specific to the linked model revision, benchmark revision, runtime contract, and host. Changing weight precision, KV-cache precision, reasoning mode, template, or speculative depth creates a different benchmark candidate.