Qwen3.8-27B-4bit-mtp

EigenLabs/Qwen3.8-27B-4bit-mtp

Qwen3.8-27B-4bit-mtp is a image-text-to-text model from EigenLabs. Use it for the image-text-to-text 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.

This is EigenLabs/Qwen3.8-27B-4bit at exact revision 301e9e2767fd0efcfab7883004720ba3c9a552a1 with the previously separate MTP proposal head (EigenLabs/Qwen3.8-27B-MTP-4bit at exact revision 329261c5e0b3f9c233485e682c…

Downloads · 30 days

176

43% of all-time downloads

All-time downloads

414

Public

Parameters

27.8B

16.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors16.3 GB · 100%

Parameter types

How the weights are stored.

U3227.3B · 98%

Try a prompt

Base models

Qwen/Qwen3.8-27B

Model card

From the Hugging Face model README

Qwen3.8-27B MLX W4/g64 + Embedded W4 MTP

This is EigenLabs/Qwen3.8-27B-4bit at exact revision 301e9e2767fd0efcfab7883004720ba3c9a552a1 with the previously separate MTP proposal head (EigenLabs/Qwen3.8-27B-MTP-4bit at exact revision 329261c5e0b3f9c233485e682cb3b67b88c20a55) embedded in the same indexed safetensors weight set under the mtp.* prefix.

Target and vision tower tensors: byte-identical to the pinned target revision.
MTP head tensors: byte-identical to the pinned head revision (W4/g64 affine, BF16 scales/biases, one full-attention layer, ~239 MB), re-keyed from the standalone layout (fc.weight, layers.0.*, …) to mtp.*.
Declared via mtplx_mtp / mtplx_mtp_quantization in config.json (prefix: "mtp.", block_size: 3). The head shares the target embedding and LM head; the target backbone remains authoritative for token acceptance and final output.

This repository supersedes the external-head pairing: the draft/target revision pins that previously lived in a README are now structural — one manifest, one weight hash, nothing to drift.

Measured (M4 Max, 546 GB/s, temperature 0)

Configuration	decode tok/s
target only	20.3–20.6
embedded MTP	28–31.5

Task: Image-Text-to-Text
Library: mlx
Type: qwen3_5
License: apache-2.0
Created: Aug 31, 2026
Updated: Aug 31, 2026