⚡ Local Inference Recipes

English | 简体中文 | 日本語

MiniMax H3: local inference speed (tok/s), sourced

As of 2026-11-14, this dataset has 18 recipes for MiniMax H3. 10 were measured by the poster. These are image, video, or audio results. Speed is in the metric column, not tok/s. 6 entries have a date, from 2026-09-02 to 2026-10-10.

Filter these in the explorer →

ModelEngineHardwaretok/sMetricSource levelDateSource
MiniMax H3 (base, 50-step class)ComfyUIRTX 50901280×736×5s: 242 s → 168 sMeasuredlink
MiniMax H3 vs FastH3 TurboUnspecifiedRTX 509015 s clip: 11 min 55 s vs 2 min 6 sMeasuredlink
MiniMax H3 (turbo)ComfyUIRTX 40905 s clip ~91 s; 15 s ~8 minutes; 960×544×5s about 50 sMeasuredlink
MiniMax H3ComfyUIRTX 309011 s video 13 minutesMeasuredlink
MiniMax H3 (Sol accelerated / not accelerated)NVIDIA Sol1× DGX SparkSol: 480p 5 s ≈ 68 s (NVIDIA published 56 s); without Sol >400 s; without Sol 720p 20 steps: 5 s 7 min / 10 s ~20 min / 15 s ~45 minMeasuredlink
MiniMax H3 vs LTX-2.3 ErosUnspecified1× DGX Spark864×480×5s: H3 average 270 s; LTX 154 s (1.76× faster)Measuredlink
FastH3 (4 steps)MLXMacBook Pro M5 Max 128GB1024×576×15 s: 43.7 → 13.3 minutesMeasuredlink
MiniMax H3Unspecified48GB Apple Silicon Mac (chip not stated)5 s clip: 35 minutes → ~8 minutesMeasuredlink
MiniMax H3TensorFoldRTX 5070 Ti 16GB + 64GB RAM (Windows)1344×768 5s with audio: 81 s (stock ComfyUI, 20 steps: 623 s)Measured2026-10-03link
MiniMax H3ComfyUILaptop RTX 5090 24GB + 64GB RAMThree 5s chained clips: 17 min totalMeasured2026-09-22link
FastH3 V2 (MiniMax H3 8-step distillation)UnspecifiedRTX 5090 32GB832×480×5s: 14.8 s; 1344×768×5s: 38.6 s (with audio, end-to-end)Official2026-10-06link
FastH3 Trim (42 blocks pruned, experimental)UnspecifiedRTX 5090480p 5s: 13.4 s; 768p: 35.4 sOfficiallink
FastH3 V2 / TrimUnspecifiedRTX 4090 24GB480p 5s: 54.6 / 43.9 s; 768p: 154.6 / 132.8 s; 8GB limit Trim 82.0 sOfficiallink
FastH3 V2 / TrimUnspecified1× / 2× DGX Spark1×: 480p 141.4 / 125.8 s, Trim 768p 340.1 s; 2×: 87.2 / 78.3 sOfficiallink
FastH3 TrimMLXMac M4 Max 36GB480p 5s: 925.2 s (V2 not listed)Officiallink
FastH3 Preview (4 steps)MLXMac M4 Max 36GB832×480×124 frames: cold start 465–504 s; INT6 456 s (peak 19.5GiB)Official2026-09-02link
MiniMax H3 Ref2VA (VSA + Turbo 4-step)ComfyUIRTX 4090 24GB1344×768×5.16s (24 fps / 124 frames): warm wall time ~72 s (first run ~95.2 s); peak VRAM ~13.5 GB. Same machine/seed/resolution: native dense 50-step ~650 s / ~22.5 GB; Turbo LoRA dense 4-step ~190 s / ~21.0 GB; VDN-H3 8-step ~135 s / ~18.5 GB (author table: first-run ~2.24× vs VDN; warm ~9× vs native)Official2026-09-05link
MiniMax H3LightX2VRTX 5090768×1344 15s video + audio ≈72 s (steady state, excl. MP4 export; baseline ~26 min)Official2026-10-10link

Numbers come from each source. This project did not measure them again. Models and settings differ between rows. Source levels: Official = project or vendor; Measured = the poster ran it (an engine or recipe author must also publish raw data and reproduction steps); Relayed = second-hand; Claimed = prediction or no reproduction details.