MinimaxH3, using Tesla V100 GPUs, dual-card parallel generation
［ninfer v100X2］v100 achieves new glories! qwen3.8 27b nvfp4 2000t/s prefill, 115t/s decode
［Ninfer V100X2］v100 achieves glory again! qwen3.8 27b nvfp4 peak 236t/s decoding, 2000t/s prefill
Tesla V100 16GB GPU, purchased for 980 yuan, miniMax H3 image-to-video generation 1280*736 resolution
V100 32GB PCIe using llama.cpp locally inferencing Qwen3.8-27B on Windows, averaging nearly 50 tps — sharing the optimal settings and some tips
V100 unlocked NVFP4, GLM5.3F insane output 145 toks
V100 boosts performance by 22,100%! Is NVLink the only viable path? MoE model tests reveal the truth.
Tesla V100 Final Edition GRID Driver 582.78
Tesla T10 Quad Card vs Dual Card Local Large Model How big is the difference really?
[Chinese Dub] Qwen3.8-27B based on NInfer framework, 220 tokens per second?
Dual-card v100, the strongest inference engine in history has arrived! First in the world, second in China.
MiniMax H3 V100 16G dual-card acceleration
[ninfer-V100X2] V100 achieves glory yet again, real-world usage non-benchmark scenario 183t/s decoding, 2500t/s prefill
Tesla V100 flawlessly runs ComfyUI with MINIMAX H3 super acceleration; a brand new wangyi-V100-ComfyUI dedicated integration package is released.
Dual V100 32g+16g mixed
Qwen3.8 27b quantized version Ternary Bonsai 2 27B Pelican riding a bicycle test
Local deployment of Qwen3.8-Flash-Next-Q4_K_M with 12+64, supporting 1M context
Dual 2080Ti Qwen3.8 27B single-concurrency extreme speed exceeds 200tk/s
Dual RTX 2080 Ti + Qwen3.8-27B-FP8, blazing 150+ TPS! Fastllm GUI rapid deployment, context can be maxed out
Someone still running qwen3.8 27b with q4 quantization complaining about high hallucinations? A minute to explain what exactly is the difference between q4 q6 fp8 bf16 nvfp4!?
