［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
The strongest 4-card V100 inference engine in history! Number one in the world, number two in China!
The Best Cost-Effective AI Local Deployment in 2025! Dual V100! 32G VRAM, High Performance at Low Price, Crushing 2080Ti 22G!
God-level project Strata! Two V100s running Qwen3.8 Flash IQ3_S, tested at 60-100 tokens/s
【刚哥玩生态】双V100 Nvlink模型服务器起飞了
V100 Duo! Two V100s running NInfer NVFP4, 27B model breaks 110 tokens/s?
👉 The internet is exploding! 24 people made a chip "only capable of 8B" but it runs at 17,000 tokens/s? Inference costs shattered? Taalas 17,000 tokens/s live demo
Four 170HX + DDR3, fully loaded DeepSeek V4.1 Flash 1017 running at 50+ tokens/s for a single stream!
Deep Evaluation of Dual V100 Reasoning Capabilities: Peloton Cycling Test in Practice
Strata model selection: run out of memory and go to SSD? First finish reading this downgrade table
【Save Money Tips】A 500-yuan NVIDIA V100 16G can run vllm: qwen3.8 27b, with speeds up to 200 tokens/s
World's first AMD discrete GPU publicly runs Qwen3.8 Flash Next text inference
The sky is falling! V100 + 3080 running Strata on an X99 motherboard hit an unbelievable 197 tokens/s! Includes a Modpack with one-click download, start your own AI life
Local model Qwen3.8 (choose 27B or flash-next-strata)
2080Ti 22g + 48g RAM running Qwen3.8-Flash-Next (IQ3_XXS): stable 45+ tok/s, amazing results
Qwen3.8_flash-IQ3-xxs local infinite token solution: 2 2080ti 22g graphics cards plus 48g memory enables local infinite tokens
2080Ti 137tok/s can still fight: ninfer+kvmem+actkv
V100 Spark Adapter Board Installation Tutorial
No words needed, just look at the picture. Dual V100 64G running Qwen 3.8 Flash NEXT. 256K context, peak 190 tokens/s.
