Run DeepSeek-V3 on $47 Hardware with Pruning and Quantization
StefanoGogioso · x · 2026-08-23
This repository demonstrates running DeepSeek-V3-Flash (mistakenly referred to as v4) on a budget of around $47, achieving 47 tok/s and a 400k context window.
Key techniques include:
- exl3 3-bit quantization.
- 18.5% model pruning.
- Stacking pruning on top of quantization is highlighted as crucial for pushing the hardware floor even lower.
Related event: DeepSeek-V3-Flash Runs at 47 tok/s on a Single $47 Setup(2 posts)→
More from Infra
- engy.ai processes 50B+ tokens in a day as open-model inference demand surges — const_reborn · 2026-10-16
- New inference engine 'e' hits 10,500 tok/s on a single DGX Station — brandon_galang · 2026-10-16
- SGLang ships Day-0 support for FLUX 3 Image Klein: 10 reference images, BF16/FP8/NVFP4 variants — ying11231 · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Chip equipment beats bull case: 2026 WFE seen at $153B, $278B by 2030 — BenBajarin · 2026-10-16
- Steam now launches in 5.23s, beating Epic's 5.47s — and vLLM gets roasted for slow startup — AlpinDale · 2026-10-16