Downloads · 30 days
169
2% of all-time downloads
MiniMax-M3-W4A16-GPTQ
Sebesky/MiniMax-M3-W4A16-GPTQ
MiniMax-M3-W4A16-GPTQ is a image-text-to-text model from Sebesky. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
4-bit weight quantization of MiniMax-M3 produced with GPTQ via llm-compressor, stored in the compressed-tensors pack-quantized format for serving with vLLM / SGLang. Routed-expert weights keep the base w1/w2/w3 naming…
All-time downloads
6.8K
Public
Parameters
430B
448 GB on disk
Likes
4
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors224 GB · 100%
Parameter types
How the weights are stored.
I32425B · 99%
Try a prompt
Base models
Model card
From the Hugging Face model README
MiniMax-M3 — W4A16 (GPTQ)
4-bit weight quantization of MiniMax-M3 produced with GPTQ via
llm-compressor, stored in the
compressed-tensors pack-quantized format for serving with vLLM / SGLang. Routed-expert
weights keep the base w1/w2/w3 naming, so the checkpoint loads against the native M3
architecture.
Quantization
| Scheme | W4A16 (4-bit weights, 16-bit activations) |
| Weights | int4, symmetric, group size 128 |
| Embeddings | int4, group size 64 |
lm_head | bf16 (kept full precision) |
| Left in bf16 | router gates, lightning-indexer projections, RMSNorms, vision tower |
| KV cache | bf16 |
| Method | GPTQ — Hessian error minimization with cross-layer error propagation |
| Format | compressed-tensors (pack-quantized) |
All 60 decoder layers are quantized (3 dense + 57 sparse/MoE, 128 experts each).
Calibration
Calibrated on deployment-realistic agentic trajectories — 427 multi-turn tool-use rollouts (~8M tokens) rendered through the M3 chat template at up to 32k sequence length, padded with a small amount of general-instruction data. The goal is to match the model's real serving distribution (multi-turn, tool-calling) rather than generic web text.
Quality
Mean weight-reconstruction error vs the bf16 base is ≈0.125 relative (cosine ≈ 0.993) — the expected magnitude for int4 group-128 quantization. This is a weight-space measure; evaluate downstream quality on your own target benchmark.
Usage
# requires a vLLM build with MiniMax-M3 support
vllm serve Sebesky/MiniMax-M3-W4A16-GPTQ
from transformers import AutoModelForImageTextToText, AutoTokenizer
model = AutoModelForImageTextToText.from_pretrained("Sebesky/MiniMax-M3-W4A16-GPTQ", device_map="auto")
tok = AutoTokenizer.from_pretrained("Sebesky/MiniMax-M3-W4A16-GPTQ")
License
Inherits the MiniMax Community License from the base model (non-commercial use).
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- minimax_m3_vl
- License
- other
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026