What can a RTX 2080 Ti 11GB run?
11GB · 616 GB/s · 250W · $280
Aged like fine wine — old stock sells for peanuts while still hitting 60+ tok/s on small Q4s.
Runs great14
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 | 308 tok/s | 33k |
| Gemma-3n-E4B | Q8_0 | 256 tok/s | 59k |
| SmolLM2-1.7B | FP16 | 112 tok/s | 8k |
| Phi-4-mini | Q8_0 | 94 tok/s | 60k |
| Gemma-3-4B | Q8_0 | 93 tok/s | 60k |
| Qwen3-4B | Q8_0 | 92 tok/s | 33k |
| Llama-3.1-8B | Q5_K_M | 67 tok/s | 33k |
| Qwen3-8B | Q5_K_M | 67 tok/s | 33k |
| Mistral-7B-Instruct | Q6_K | 64 tok/s | 32k |
| DeepSeek-R1-Distill-Qwen-7B | Q6_K | 61 tok/s | 28k |
| Qwen2.5-Coder-7B | Q6_K | 61 tok/s | 28k |
| Llama-3.2-3B | FP16 | 59 tok/s | 36k |
Tight squeeze7
It fits, but close the browser tabs and mind the context.
| Model | Quant | Est. speed | Max context |
|---|---|---|---|
| GPT-OSS-20B | IQ2_M | 314 tok/s | 17k |
| Codestral-22B | IQ2_M | 51 tok/s | 14k |
| Gemma-3-12B | Q4_K_M | 49 tok/s | 13k |
| Mistral-Small-24B | IQ2_M | 47 tok/s | 9k |
| Qwen3-14B | Q3_K_M | 46 tok/s | 9k |
| Phi-4-14B | Q4_K_M | 43 tok/s | 4k |
| DeepSeek-R1-Distill-Qwen-14B | Q4_K_M | 43 tok/s | 4k |
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.