Builds / 8x RTX 3090 24 GB
8x RTX 3090 serving DeepSeek V4 Flash (LimeChain vLLM kit)
Source: github.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
Legacy models only. Every model measured on this rig now has a newer successor: DeepSeek V4 Flash → DeepSeek V4.1 Flash. The hardware numbers are still a useful reference.
- GPU(s)
- 8x RTX 3090 24 GB
Amazon · eBay (used) · Newegg - VRAM / unified memory (GB)
- 192
- CPU
- not stated
- Motherboard
- not stated
- RAM
- not stated
- PSU
- not stated
- Other
- vLLM SM86 overlay, PP8/TP1, DSpark speculative decoding
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Details |
|---|---|---|---|---|
| DeepSeek V4 Flash legacy | 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?