Downloads · 30 days
33
62% of all-time downloads
empero-ai-Qwen3.8-4B-Distill-MTPLX
Lancelotbronner/empero-ai-Qwen3.8-4B-Distill-MTPLX
empero-ai-Qwen3.8-4B-Distill-MTPLX is a machine learning model from Lancelotbronner. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from empero-ai/Qwen3.8-4B-Distill.
All-time downloads
53
Public
Parameters
4.2B
2.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.6 GB · 99%
Parameter types
How the weights are stored.
U324.2B · 100%
Model card
From the Hugging Face model README
empero-ai-Qwen3.8-4B-Distill-MTPLX
MTPLX-branded multi-token-prediction model for Apple Silicon (MLX).
Forged with MTPLX Forge from
empero-ai/Qwen3.8-4B-Distill.
Verification
- Best depth: D2
- Multiplier vs autoregressive baseline: 1.53×
- Verified on: Apple M4 Pro
- 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 <owner>/empero-ai-Qwen3.8-4B-Distill-MTPLX
mtplx start chat
License
See LICENSE.
- Type
- qwen3_5
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026