nvidia / text-generation updated 1 month ago

MiniMax-M3-NVFP4

Name: MiniMax-M3-NVFP4
Author: nvidia

MiniMax-M3 is a multimodal model with frontier-level coding and agentic capabilities, built on a Mixture-of-Experts architecture with a 1M-token context window. The model processes text, image, video, and computer use inputs and produces text outputs, with emphasis on long-horizon coding tasks, agentic and tool-use workflows, and long-form video understanding. The NVIDIA MiniMax-M3 NVFP4 model is quantized with Model...

Params

246.6 B

Context

—

Downloads 30d

557 K

Likes

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

591 K557 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	250.1 GB	312.6 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/minimax-m3-nvfp4
{
  "hf_id": "nvidia/MiniMax-M3-NVFP4",
  "params_b": 246.63,
  "context_length": null,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 556501,
  "vram_estimates": [
    { "quant": "u8", "gb": 312.6 }
  ],
  "updated_at": "2026-07-28T18:04:51Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: MiniMaxM3SparseForConditionalGeneration
Parameters: 246.6 B
Tensor type: U8
Licence: other
First seen on the Hub: 2026-06-23
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

DeepSeek-R1 9.9 M gpt-oss-120b 4.2 M DeepSeek-V4-Flash 2.7 M GLM-5.2-FP8 2.7 M GLM-5.2-NVFP4 1.8 M MiniMax-M2.7 924 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB