Qwen3.6-35B-A3B-MTPLX-Optimized-Speed

Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed

Qwen3.6-35B-A3B-MTPLX-Optimized-Speed is a text generation model from Youssofal. Use it when you need the model to write or continue text. It is set up for mtplx. The card lists the license as apache-2.0.

Fast local 35B-A3B inference for Apple Silicon, packaged for MTPLX native Multi-Token-Prediction speculative decoding.

Downloads · 30 days

3.3K

37% of all-time downloads

All-time downloads

Public

Parameters

35.1B

21 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors21 GB · 100%

Parameter types

How the weights are stored.

U3234.7B · 99%

Try a prompt

Model card

From the Hugging Face model README

Qwen3.6-35B-A3B MTPLX Optimized Speed

Fast local 35B-A3B inference for Apple Silicon, packaged for MTPLX native Multi-Token-Prediction speculative decoding.

This is the speed-focused 35B checkpoint: a compact 4-bit MLX body with calibrated INT4 MTP heads, tuned so MTPLX can draft more confidently and verify less work per generated token.

Run It

brew install youssofal/mtplx/mtplx
mtplx start
mtplx run "hello" --model Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed

For an OpenAI-compatible local server:

mtplx serve --model Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed --profile sustained --max --port 8000 --no-stats-footer

Why This Exists

MTPLX uses the model's own MTP heads to generate draft tokens, then verifies them with the main model. When the draft heads are well-matched, you get higher throughput without using a separate drafter model.

This checkpoint is optimized for that path. MTPLX reads mtplx_runtime.json and selects the measured speed defaults automatically.

Recommended Runtime Defaults

Setting	Value
Backend	`qwen3-next-mtp`
Default depth	`D1`
Verifier strategy	`target_prefix`
Target sampler	`temp=0.60`, `top_p=0.95`, `top_k=20`
Draft sampler	`temp=0.60`, `top_p=0.95`, `top_k=20`
Profile	`sustained`
Benchmark fan mode	`max`

Performance

Measured in MTPLX Sustained Max on Apple Silicon with reasoning enabled and a 32k token response allowance. All recorded runs finished naturally without a length stop.

Mode	TPS	Verify time	Acceptance
AR baseline	94.46	-	-
D1 promoted default	138.39	69.30s	0.8858
D2 comparison	135.66	49.23s	0.8701, 0.6409
D3 comparison	107.67	46.45s	0.8291, 0.5414, 0.2783

D1 is the promoted default because it gives the best real-use balance: strong TPS, high acceptance, and lower verify cost than the earlier 35B speed baseline.

Model Build

Component	Format
Main body	4-bit MLX affine, group size 64
Router and gate tensors	8-bit where recorded by config
MTP numbered-expert weights	calibrated INT4, group size 32
Norms, scales, biases, plain tensors	BF16

This is not a full-precision checkpoint. It is built for fast local use on Apple Silicon through MTPLX.

Files

model-*.safetensors: MLX 4-bit body shards
mtp.safetensors: calibrated INT4 MTP sidecar
mtplx_runtime.json: MTPLX runtime contract and measured defaults
MTPLX_PUBLISH_MANIFEST.json: file sizes and benchmark summary
tokenizer and config files for local loading

Task: Text Generation
Library: mtplx
Type: qwen3_5_moe
License: apache-2.0
Created: Jun 6, 2026
Updated: Sep 17, 2026