Can Kimi VL A3B Thinking 2506 run on the RTX 4070 Ti?
Yes. At 8K context the best fit is Q3_K_M, using about 8.4 GB of the 11.4 GB usable on the RTX 4070 Ti. Estimated speed ceiling: ~344 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) | 6.6 GB Fits | 6.7 GB Fits | 7.4 GB Fits | 10.2 GB Fits | 448 |
| 3-bit (Q3_K_M) | 8.3 GB Fits | 8.4 GB Fits | 9.1 GB Fits | 12.0 GB No | 344 |
| 4-bit (Q4_K_M) • | 10.6 GB Tight | 10.8 GB Tight | 11.5 GB No | 14.3 GB No | 262 |
| 5-bit (Q5_K_M) | 11.7 GB No | 11.8 GB No | 12.5 GB No | 15.4 GB No | — |
| 6-bit (Q6_K) | 13.4 GB No | 13.5 GB No | 14.2 GB No | 17.0 GB No | — |
| 8-bit (Q8_0) • | 16.6 GB No | 16.8 GB No | 17.5 GB No | 20.3 GB No | — |
| 16-bit (F16/BF16) • | 60.3 GB No | 60.4 GB No | 61.1 GB No | 64.0 GB No | — |
• real GGUF file size from ggml-org/Kimi-VL-A3B-Thinking-2506-GGUF. Speed is a bandwidth ceiling (504 GB/s), not a benchmark. Methodology.
More
Kimi VL A3B Thinking 2506 on every GPU and Mac · Every model that runs on the RTX 4070 Ti · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (moonshotai/Kimi-VL-A3B-Thinking-2506), NVIDIA specs. Data as of 2026-11-17.