中文Sign up

sahilchachra/orcarouter-Qwen3.8-27B-Uncensored-MXFP8

🤗 Hugging Face sourceimage-text-to-textapache-2.027.4B params55 GBsafetensors✓ 27 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo sahilchachra/orcarouter-Qwen3.8-27B-Uncensored-MXFP8 ./model-folder
Needs a seeder →

orcarouter-Qwen3.8-27B-Uncensored — MLX MXFP8

MLX MXFP8 quantization of orcarouter/Qwen3.8-27B-Uncensored, an uncensored fine-tune of Qwen3.8-27B. Qwen3.8-27B is a qwen3_5 vision-language model with a hybrid GatedDeltaNet linear-attention + full-attention text backbone (64 layers, full attention every 4th) and a Qwen3-VL vision tower. Runs on Apple Silicon via mlx-vlm. Stays image-text-to-text — the vision tower is kept in bf16; only the text backbone is quantized.
Precision MXFP8 (E4M3 + E8M0 shared scale, group size 32)
Bits per weight 8.381 bpw
On-disk size 27 GB (26 shards)
Quantized text backbone (incl. the ~1.27B lm_head)
Kept in bf16 Qwen3-VL vision tower

Quantizations

Variant Bits Size
orcarouter-Qwen3.8-27B-Uncensored-MXFP4 4.449 bpw 14 GB smaller / for 16 GB+
orcarouter-Qwen3.8-27B-Uncensored-MXFP8 8.381 bpw 27 GB ← this repo

Verification

This higher-fidelity build was verified structurally (correct tensor shapes, format: mlx metadata, consistent shard index, vision tower intact in bf16). Full token-by-token generation was not benchmarked on the 24 GB test machine because 27 GB exceeds its RAM; on a 32 GB+ Mac it runs at normal speed. Since MXFP8 uses more bits than the MXFP4 build — which passed text + vision smoke tests end-to-end — it is at least as faithful to the base model.

See the MXFP4 build for the full generation/vision smoke-test results.

Usage (mlx-vlm)

pip install -U mlx-vlm   # needs the qwen3_5 architecture (>= 0.6.12)

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template

model, processor = load("sahilchachra/orcarouter-Qwen3.8-27B-Uncensored-MXFP8")
config = model.config

prompt = apply_chat_template(processor, config, "What is the capital of France?")
print(generate(model, processor, prompt, max_tokens=256, verbose=True))

This is a reasoning model; it produces a <think> channel before its answer.

Run in LM Studio

Loads and runs in LM Studio (tested on 0.4.20, mlx-llm runtime): the qwen3_5 architecture is recognized, the model indexes cleanly (format: mlx present), and the ChatML template runs as-is. This is a reasoning model — it emits a thinking channel (reasoning_content) before the final content, so give it enough max_tokens (e.g. 200+) or the answer can be empty while it is still thinking. Verified: "capital of France" → reasoning + content = "Paris".

Note: at 27 GB this needs a 32 GB+ Mac to load under LM Studio's default guardrails.

Notes & limitations

  • Uncensored model. This is a deliberately uncensored/abliterated derivative and will not refuse requests the way the original might. Use responsibly and in line with the base model's license and your local laws.
  • MTP head dropped. The base model's multi-token-prediction (speculative decoding) head is not included — mlx-vlm strips the mtp.* weights on load. Text and vision are unaffected; only spec-decode is not available.
  • tie_word_embeddings=false, so the ~1.27B lm_head is a separate matrix and is quantized. Verified correct on the MXFP4 build above.
  • Inherits all capabilities and limitations of the base model. See the original model card.
  • Quantized by @sahilchachra with MLX. Apache-2.0.