Downloads · 30 days
841
23% of all-time downloads
itrejomx/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTPLX-4bit
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTPLX-4bit is a machine learning model from itrejomx. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
MLX 4-bit build of HauhauCS's Qwen3.8-27B Uncensored Aggressive fine-tune with a working multi-token-prediction (MTP) head, forged and verified with MTPLX (contract=true).
Downloads · 30 days
841
23% of all-time downloads
All-time downloads
3.7K
Public
Parameters
26.9B
16 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors16 GB · 100%
How the weights are stored.
U3226.9B · 100%
From the Hugging Face model README
MLX 4-bit build of HauhauCS's Qwen3.8-27B Uncensored Aggressive fine-tune with a working multi-token-prediction (MTP) head, forged and verified with MTPLX (contract=true).
At ~16 GB this fits 24/32 GB Macs. If you have 32 GB+ and want higher fidelity, use the 6-bit build.
| Mode | decode tok/s | vs AR |
|---|---|---|
| Autoregressive | 14.9 | 1.00x |
| MTP depth 1 | 31.0 | 2.08x |
| MTP depth 2 | 37.3 | 2.51x |
| MTP depth 3 | 32.5 | 2.18x |
MTPLX auto-tunes the depth per machine; on the build machine depth 2 was selected.
mtplx pull <this-repo>
mtplx tune --model <this-repo> --retune # calibrate MTP depth for your machine
This is a community conversion, not an official HauhauCS release (their releases carry Ed25519-signed manifests; this one does not).
mtp_policy: keep_bf16) and was verified against the trunk.A_log as -exp(A_log); both transforms were inverted to restore the HF/MLX layout before forging.enable_thinking: true to turn it back on.<think>/</think> special-token registration, which the GGUF metadata round-trip loses.