DeepSeek v4.1 Flash runs locally at 27 tok/s decode with 256k context on an RTX 5090
QuixiAI · x · 2026-11-08
QuixiAI reports running DeepSeek v4.1 Flash (1017) locally on an RTX 5090, hitting 27 tok/s decode and 161 tok/s prefill at 256k context. This follows casperhansen's claim of 15 tok/s on an RTX 3090 build ($2.5k), with a roadmap of building his own inference engine, an undetected browsing plugin, a new quantization framework, then having AI iterate over those steps. Local inference of frontier-class models is becoming genuinely viable on consumer hardware.
Related event: Running DeepSeek V4.1 Flash Locally: 27 tok/s on an RTX 5090(3 posts)→
More from Infra
- TSMC denies 3D DRAM plans at Nvidia's request, stays pure-play logic foundry — rohanpaul_ai · 2026-11-08
- TSMC denies developing 3D DRAM at Nvidia's request, staying a pure logic foundry — rohanpaul_ai · 2026-11-08
- Why is everyone sleeping on Modal live inference endpoints for agents? — vboykis · 2026-11-08
- Arista CEO forecasts 10+ GW of AI deployments across 10+ accelerator types by end of 2027 — Beth_Kindig · 2026-11-08
- Hugging Face launches live training streams, starting with RL-tuned LoRA adapters — art_zucker · 2026-11-08
- Lobsters thread: how AI traffic is degrading the web for human developers — vboykis · 2026-11-08