Can deepseek vl2 tiny run on the Arc A770 16GB?
Yes. At 8K context the best fit is F16, using about 7.4 GB of the 15.2 GB usable on the Arc A770 16GB. Estimated speed ceiling: ~238 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | Max tok/s (est., 8K) |
|---|---|---|
| 2-bit (Q2_K) | 2.1 GB Fits | 1271 |
| 3-bit (Q3_K_M) | 2.4 GB Fits | 975 |
| 4-bit (Q4_K_M) | 2.8 GB Fits | 779 |
| 5-bit (Q5_K_M) | 3.1 GB Fits | 669 |
| 6-bit (Q6_K) | 3.5 GB Fits | 581 |
| 8-bit (Q8_0) | 4.2 GB Fits | 448 |
| 16-bit (F16/BF16) | 7.2 GB Fits | 238 |
• real GGUF file size. Speed is a bandwidth ceiling (560 GB/s), not a benchmark. Methodology.
More
deepseek vl2 tiny on every GPU and Mac · Every model that runs on the Arc A770 16GB · Other models that fit 16 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (deepseek-ai/deepseek-vl2-tiny), Intel specs. Data as of 2026-11-17.