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

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

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

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

Downloads · 30 days

758

12% of all-time downloads

All-time downloads

6.2K

Public

Parameters

35.1B

29.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors29.6 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 Balance

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

This checkpoint is the balanced 35B release: a 6-bit MLX body paired with calibrated INT4 MTP heads. It is tuned for strong reasoning-on generation speed while keeping prompt processing and memory use practical across normal coding contexts.

Run It

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

For an OpenAI-compatible local server:

mtplx serve --model Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance --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 running a separate drafter model.

Optimized Balance is built for that path. MTPLX reads mtplx_runtime.json and selects the measured D2 defaults automatically.

Recommended Runtime Defaults

Setting	Value
Backend	`qwen3-next-mtp`
Default depth	`D2`
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.

Generation

Mode	TPS	Verify time	Acceptance
AR baseline	86.30	-	-
D1 comparison	123.00	7.24s	0.8329
D2 promoted default	126.43	6.62s	0.8134, 0.5048
D3 comparison	112.43	7.16s	0.7802, 0.4709, 0.2514

D2 is the promoted default because it gives the best balance of throughput, acceptance, and verify cost. A three-run D2 repeat averaged 123.44 tok/s, with every run above 122 tok/s.

Prompt Processing

Context	Prompt TPS
512	1,756.8
1k	3,339.2
2k	4,109.8
4k	4,048.7
8k	3,872.0
16k	3,162.3
32k	2,761.3
64k	1,834.2

Average prompt processing across the 512-to-64k ladder was 3,110.5 tok/s.

Model Build

Component	Format
Main body	6-bit MLX affine, group size 64
Router and gate tensors	8-bit where recorded by config
MTP numbered-expert weights	INT4 MLX affine, group size 64
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 6-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