8x RTX 3090 serving DeepSeek V4 Flash (LimeChain vLLM kit)
| GPU(s) | 8x RTX 3090 24 GB Amazon · eBay (used) · Newegg |
|---|---|
| VRAM / unified memory (GB) | 192 |
| CPU | |
| Motherboard | |
| RAM | |
| PSU | |
| Other | vLLM SM86 overlay, PP8/TP1, DSpark speculative decoding |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| DeepSeek V4 Flash | see source (FP8 KV cache) | vLLM LimeChain SM86 overlay, 1 concurrent request | 95.52 | 📏 Per-session end-to-end p50 at concurrency 1, 128 generated tokens |
Model is DeepSeek-V4-Flash-0731. Per-session end-to-end p50 at concurrency 1, 128 generated tokens; aggregate reaches ~404 tok/s at 12 concurrent. The README calls it screening-only. Found via localmaxxing (discovery only); numbers re-checked at the original source on 2026-10-24.
Source: https://github.com/LimeChain/vllm/tree/deepseek-v4-flash-sm86/release/limechain-sm86
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)
Quick answers: Can 8x RTX 3090 run DeepSeek V4 Flash?