Downloads · 30 days
10
9% of all-time downloads
Qwen-Qwen3.5-35B-A3B-Base-MTPLX
mschemerii/Qwen-Qwen3.5-35B-A3B-Base-MTPLX
Qwen-Qwen3.5-35B-A3B-Base-MTPLX is a machine learning model from mschemerii. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from Qwen/Qwen3.5-35B-A3B-Base.
All-time downloads
117
Public
Parameters
34.7B
21.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors21.2 GB · 100%
Parameter types
How the weights are stored.
U324.3B · 80%
Base models
Model card
From the Hugging Face model README
Qwen-Qwen3.5-35B-A3B-Base-MTPLX
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX).
Forged with MTPLX Forge from
Qwen/Qwen3.5-35B-A3B-Base.
Verification
- Best depth: D1
- Multiplier vs autoregressive baseline: 1.36×
- Verified on: Apple M4 Max
- Sampler: temperature 0.6 · top_p 0.95 · top_k 20
See mtplx_runtime.json for the full verification record.
Usage
# MTPLX picks this model up automatically when downloaded:
mtplx pull mschemerii/Qwen-Qwen3.5-35B-A3B-Base-MTPLX
mtplx start chat
License
See LICENSE.
- Type
- qwen3_5_moe
- License
- apache-2.0
- Languages
- en
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026