Hardware
GeForce RTX 3090 24GB
Used card only. 24 GB and a wide bus. One card is not enough for 70B Q4.
Memory
24 GB VRAMBandwidth
936 GB/sBandwidth source is not stored.
Price
$806€720
14 Oct 2026
price unverifiedWhich models fit
Estimate at 8,192 tokens, or the model's maximum when that is shorter. full means the formula fits in usable memory. offload means GPU plus system RAM. no means it does not fit. This is not a measured file.
| Model | Q4estimate | Q5estimate | Q8estimate | FP16estimate |
|---|---|---|---|---|
| Llama 3.2 3B | full | full | full | full |
| Llama 3.1 8B | full | full | full | full |
| Mistral 7B v0.3 | full | full | full | full |
| Gemma 2 9B | full | full | full | full |
| Qwen2.5 14B | full | full | full | no |
| Phi-4 14B | full | full | full | no |
| Gemma 2 27B | full | full | no | no |
| Qwen2.5 32B | full | no | no | no |
| Llama 3.3 70B | no | no | no | no |
| Qwen2.5 72B | no | no | no | no |
| DeepSeek-R1-Distill 70B | no | no | no | no |