Hardware
Mid-range PC with RTX 4060 Ti 16GB
16 GB is comfortable for 14B. Bandwidth is lower than a 3060, so 8B is not automatically faster.
Memory
16 GB VRAMBandwidth
288 GB/sBandwidth source is not stored.
Price
$1,668€1,490
14 Oct 2026
price unverifiedParts in the catalog
- GeForce RTX 4060 Ti 16GB
- Ryzen 5 7600 or similar
- 64 GB DDR5
- 1 TB SSD
Which 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 | offload |
| Mistral 7B v0.3 | full | full | full | offload |
| Gemma 2 9B | full | full | full | offload |
| Qwen2.5 14B | full | full | offload | offload |
| Phi-4 14B | full | full | offload | offload |
| Gemma 2 27B | offload | offload | offload | offload |
| Qwen2.5 32B | offload | offload | offload | offload |
| Llama 3.3 70B | offload | offload | no | no |
| Qwen2.5 72B | offload | offload | no | no |
| DeepSeek-R1-Distill 70B | offload | offload | no | no |