Can Yi 6B run on the RTX 3080 12GB?
Yes. At 8K context the best fit is Q8_0, using about 7.0 GB of the 11.4 GB usable on the RTX 3080 12GB. Estimated speed ceiling: ~142 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) • | 2.9 GB Fits | 390 |
| 3-bit (Q3_K_M) • | 3.6 GB Fits | 305 |
| 4-bit (Q4_K_M) • | 4.2 GB Fits | 248 |
| 5-bit (Q5_K_M) • | 4.8 GB Fits | 212 |
| 6-bit (Q6_K) • | 5.4 GB Fits | 183 |
| 8-bit (Q8_0) | 6.8 GB Fits | 142 |
| 16-bit (F16/BF16) | 12.1 GB No | — |
• real GGUF file size from mradermacher/Yi-6B-i1-GGUF. Speed is a bandwidth ceiling (912 GB/s), not a benchmark. Methodology.
More
Yi 6B on every GPU and Mac · Every model that runs on the RTX 3080 12GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (01-ai/Yi-6B), NVIDIA specs. Data as of 2026-11-17.