What can a RTX 4060 8GB run?
8GB · 272 GB/s · 115W · $300
A dainty, cool-tempered card for 4–7B Q4 models — the power bill stays friendly all year.
Runs great9
Comfortable headroom — daily-driver territory.
| Model | Quant | Est. speed | Max context |
|---|---|---|---|
| deepseek moe 16b chat | FP16 | Infinity tok/s | — |
| qwen2 7b instruct | FP16 | Infinity tok/s | — |
| Qwen3-0.6B | FP16 | 136 tok/s | 33k |
| Gemma-3n-E4B | Q8_0 | 113 tok/s | 28k |
| SmolLM2-1.7B | FP16 | 50 tok/s | 8k |
| Llama-3.2-3B | Q8_0 | 49 tok/s | 37k |
| Phi-4-mini | Q8_0 | 41 tok/s | 28k |
| Gemma-3-4B | Q8_0 | 41 tok/s | 28k |
| Qwen3-4B | Q8_0 | 40 tok/s | 27k |
Tight squeeze9
It fits, but close the browser tabs and mind the context.
| Model | Quant | Est. speed | Max context |
|---|---|---|---|
| Gemma-3-12B | IQ2_M | 39 tok/s | 17k |
| Phi-4-14B | IQ2_M | 34 tok/s | 12k |
| DeepSeek-R1-Distill-Qwen-14B | IQ2_M | 34 tok/s | 12k |
| DeepSeek-R1-Distill-Qwen-7B | Q5_K_M | 31 tok/s | 11k |
| Qwen2.5-Coder-7B | Q5_K_M | 31 tok/s | 11k |
| Qwen3-14B | IQ2_M | 30 tok/s | 7k |
| Llama-3.1-8B | Q5_K_M | 29 tok/s | 8k |
| Qwen3-8B | Q5_K_M | 29 tok/s | 8k |
| Mistral-7B-Instruct | Q6_K | 28 tok/s | 6k |
Measured on this card0
Everything here was benchmarked on this exact card by someone who owns one — the tables above are our arithmetic; these numbers came off real machines.
Nobody has measured anything on this card yet. Paste a benchmark — it takes one keystroke and no form.