Model reference · open weights
MiniMax-H3-FL2VA-Pruned-IQ1 is an open-weight video model from MarxistLeninist, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
MiniMax H3 FL2VA Pruned — importance-guided mixed-IQ1 QF2 GGUF Experimental mixed-precision GGUF quantizations of the approximately 20B-parameter pruned MiniMax H3 FL2VA diffusion denoiser. This is not the complete H3 system; its Qwen3-VL text encoder and video/audio VAEs are separate. The repository owner confirms separate written MiniMax authorization covering this publication. That authorization is not sublicensed here; downstream users remain responsible for the official license and location-specific authorization. Artifact and quality status The original uniform IQ1S and IQ1M files are deprecated: perceptual FAIL. They load and produce valid A/V containers, but a controlled 22-frame test produced no recognizable fox or snow. QF2 is the final importance-guided mixed-precision policy. Earlier QF1 working files are superseded internal evidence, not final artifacts. The website four-step profile and eight-step full profile have separate verdicts. Do not describe either QF2 file as having passed full eight-step audiovisual generation. What QF2 means The refreshed activation importance matrix showed a steep rise through later fc1 blocks. QF2 therefore uses: - BF16: conditionproj.weight and protected one-dimensional norm/gain tensors - Q80: both token-refiner blocks and every eligible matrix in main blocks 46–49 - Q4K: mlp.fc1 in blocks 30–45, plus attention qkvproj/outproj and mlp.fc2 in all non-Q8 main blocks - IQ1S or IQ1M: only mlp.fc1 in blocks 0–29 - inherited Q80: audio/video patch-projection weights whose shapes cannot be converted to IQ1/Q4K - source precision: biases, final/output layers, and other shapes excluded by converter safeguards These are mixed-precision derivatives. IQ1 is the lowest precision and covers 4,624,220,160 parameters; the files are not uniform one-bit models. Controlled quick audit Same fox prompt, seed 11, CPU RNG, 320x192, 22 frames, 24 FPS, 4 steps, CFG 1.0: PSNR and SSIM compare decoded frames against Q8 at identical settings. LPIPS was not collected and is not claimed. Website and holdout evidence - QF2 IQ1M fox, 640x384/39 frames/4 steps: clear fox; audio RMS -15.6642 dBFS; clipped fraction 0; MP4 SHA-256 e42ee46827018f86e86b6
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | MarxistLeninist |
|---|---|
| Type | Video models |
| Variants | 1 |
| Runs with | gguf |
| Based on | MiniMaxAI/MiniMax-H3 |
| Released | 2026-08-10 |
| Popularity | 1k downloads / month |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| MiniMax-H3-FL2VA-Pruned-IQ1-GGUF | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys minimax-h3-fl2va-pruned-iq1 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-h3-fl2va-pruned-iq1 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/videos/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minimax-h3-fl2va-pruned-iq1","prompt":"a drone shot over a forest"}'
Details
Tags
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗
Explore