Qwen3.6-27B-MXFP4-MTP

<p align="center"><img src="osaurus-x-banner.png" width="100%" alt="OsaurusAI"/></p>

Qwen3.6-27B-MXFP4-MTP

Qwen3.6-27B (dense) quantized to native MXFP4 for Apple Silicon, with the vision tower and the native Multi-Token-Prediction head preserved and enabled. This is the smallest bundle in the line — full Qwen3.6-27B capability in 14 GB.

Quantization

4-bit affine linears via MLX-native mx.quantize (mode="mxfp4", group_size=32). Norms, hybrid-attention control tensors and the full vision tower are kept in fp16 passthrough. MTP linears are quantized to MXFP4; MTP norm/control tensors stay fp16.

Multi-Token Prediction

This bundle keeps Qwen3.6's native MTP module and runs it as a self-speculative draft head: the MTP head proposes tokens that the main model verifies in a single pass, so decoded output stays bit-identical to plain autoregressive decoding — only faster.

Recorded on an M5 Max (vMLX runtime, 96-token deterministic prompt, output verified equal to baseline at every depth):

On this bundle D2 is the fastest depth — D3 draws even but does not pull ahead, so the runtime selects D2 by default.

Absolute tok/s depends on free memory and system load. The speedup ratio — baseline vs. MTP measured back-to-back under identical conditions — is the stable figure.

Vision, MTP and caching together

This bundle runs image/video input, native MTP speculative decode and prefix/KV caching in the same session — a combination not every MTP-enabled Qwen build exposes. A recorded smoke test confirms both a text prompt and an image color prompt return correct answers through the combined MTP + VL runtime.

Loading

Loads via stock MLX tooling on Apple Silicon — the mxfp4 weights are native mx.quantize affine, no JANG runtime required for the core model.

from mlx_vlm import load, generate
model, processor = load("OsaurusAI/Qwen3.6-27B-MXFP4-MTP")

The MTP draft path is exercised by an MTP-aware runtime (vMLX); other runtimes load and decode the main model normally and ignore the MTP head.

Variants

Credits

• Quantization toolchain: JANG by Jinho Jang <[email protected]>
• Base model: Qwen3.6-27B by Qwen