MATLOWAI/minimax-h3-nvfp4

MiniMax H3 FL2VA pruned, NVFP4 (Blackwell)

An NVFP4 quantisation of the MiniMax H3 pruned FL2VA diffusion model for ComfyUI. Every one of the 200 block linears (qkv, out, fc1, fc2 in all 50 blocks) is stored as fp4 e2m1 with fp8 e4m3 block scales of 16 and one fp32 per-tensor scale; embeds, token refiner, norms and heads stay bf16. On Blackwell (sm120) the GEMMs run natively on the fp4 tensor cores.

Modification notice (required by the license): this repository contains a modified version of MiniMax H3. The modification is post-training weight quantisation of the block linears to NVFP4, performed 2026-08-19. Built from diffusion_models/minimax_h3_fl2va_pruned_bf16.safetensors in Comfy-Org/MiniMax-H3, revision 3f57e8291d2ef846f9a074b1b76d2767db434abe.

Should you use this file?

• RTX 50-series / Blackwell + pytorch cu130+, current ComfyUI: yes, if you want the speed. Measured against the W4A8 file on the same seed and graph: 0.84x wall at 29k tokens, 0.90x at 45k, on an RTX PRO 6000. Same file size as W4A8 (12.5 GB, both 4.54 bits per parameter), so this is a speed play, not a memory play.
• Any other GPU: no. ComfyUI falls back to dequantised matmuls, which is slower than int8_convrot. Use Comfy-Org's int8_convrot file instead.

Runs on stock ComfyUI, no custom nodes required: the file carries per-layer comfy_quant metadata, the same mechanism as the NVFP4 text encoder that Comfy-Org already ships.

How to run it

1. Blackwell GPU (RTX 50 series or RTX PRO Blackwell), pytorch built for CUDA 13.0 or newer, and a current ComfyUI updated together with its comfy-kitchen dependency.
2. Put the .safetensors in models/diffusion_models/minimax_h3/ next to the usual H3 stack from Comfy-Org (text encoder, video VAE, audio VAE).
3. Use any H3 workflow and point UNETLoader at this file, weight_dtype default. No custom nodes; the per-layer metadata does the rest.
4. Check the load log for Native ops: nvfp4. If a render comes out slower than the int8 file you are on the dequant fallback (wrong pytorch or a stale comfy-kitchen).
5. The lightx2v turbo LoRA stacks cleanly and keeps the speed: measured 12-step turbo, 210 s vs 239 s on the W4A8 file (0.88x), same graph and seed.

What it costs in quality

Median weight error is 9.4 percent relative rms vs bf16 (the W4A8 file carries 7.3, int8_convrot 1.0). In practice a same-seed render is a clean sibling take: same scene and words, slightly different delivery. Side-by-side pages with clips, pixel, flow and audio rulers, and a synced A/B player: https://matlowai.github.io/ComfyUI-MAINodes/a6-review/ (the gold cards are this checkpoint). Note that an int8 control lands in the same distance-from-reference band, so within this model family that distance measures which take you got, not how good it is. Judge with your eyes on your own content.

Rebuild it yourself

The 30-second builder script (quantises the Comfy-Org bf16 file with comfy's own TensorCoreNVFP4Layout) ships in ComfyUI-MAINodes as tools/build_nvfp4_checkpoint.py. The .census.json beside the weights holds the per-layer weight error of this exact build.

License

MiniMax H3 Community License Agreement (see LICENSE and NOTICE in this repository, and the license link above). The license carries territory restrictions and other conditions; read it before using or redistributing. Powered by MiniMax H3.