Community-built MiniMax H3 weights target 12GB–24GB GPUs with INT4 and NVFP4 variants
VoidAsuka · x · 2026-08-04
The post points to a community-compiled set of quantized and pruned MiniMax H3 weights in INT4, INT8, mixed, and NVFP4 formats.
According to the quoted text, the collection is aimed at users with 12GB–24GB VRAM GPUs, making the model more practical for consumer hardware and local experimentation.
Related event: MiniMax H3 Local Tests: Benchmark Results and Comparisons Across GPUs(88 posts)→
More from Infra
- NVIDIA launches RTX Spark for local AI on Windows PCs — ostrisai · 2026-10-16
- SkyRL ships Day-0 RL support for Beam with +62% LoRA decode throughput in vLLM — vllm_project · 2026-10-16
- DFlash2 delivers up to 3.03x decode-only speedup for Beam across five benchmarks — vllm_project · 2026-10-16
- vLLM's Beam serving kernels cut GB200 forward time from 8.15 to 6.47 ms at TP8 batch 128 — vllm_project · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Gemma 4 31B QAT on one 24GB card: 46 tok/s plain, ~80 with draft model on RTX 4090 — Subject_Poet_3861 · 2026-10-16