Can Yi 6B 200K run on the RTX 4060 Ti 8GB?
Yes. At 8K context the best fit is Q6_K, using about 5.7 GB of the 7.6 GB usable on the RTX 4060 Ti 8GB. Estimated speed ceiling: ~58 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | 3.2 GB Fits | 3.5 GB Fits | 5.0 GB Fits | 11.0 GB No | 110 |
| 3-bit (Q3_K_M) • | 3.6 GB Fits | 3.8 GB Fits | 5.3 GB Fits | 11.3 GB No | 96 |
| 4-bit (Q4_K_M) • | 4.2 GB Fits | 4.4 GB Fits | 5.9 GB Fits | 11.9 GB No | 78 |
| 5-bit (Q5_K_M) • | 4.8 GB Fits | 5.0 GB Fits | 6.5 GB Fits | 12.5 GB No | 67 |
| 6-bit (Q6_K) • | 5.4 GB Fits | 5.7 GB Fits | 7.2 GB Tight | 13.2 GB No | 58 |
| 8-bit (Q8_0) • | 6.8 GB Fits | 7.0 GB Tight | 8.5 GB No | 14.5 GB No | 45 |
| 16-bit (F16/BF16) | 12.1 GB No | 12.3 GB No | 13.8 GB No | 19.8 GB No | — |
• real GGUF file size from TheBloke/Yi-6B-200K-GGUF. Speed is a bandwidth ceiling (288 GB/s), not a benchmark. Methodology.
More
Yi 6B 200K on every GPU and Mac · Every model that runs on the RTX 4060 Ti 8GB · Other models that fit 8 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (01-ai/Yi-6B-200K), NVIDIA specs. Data as of 2026-11-17.