Can DeepSeek V2 Lite run on the Arc A770 16GB?
Yes. At 8K context the best fit is Q5_K_M, using about 11.3 GB of the 15.2 GB usable on the Arc A770 16GB. Estimated speed ceiling: ~295 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) • | 6.7 GB Fits | 6.8 GB Fits | 7.5 GB Fits | 10.4 GB Fits | 514 |
| 3-bit (Q3_K_M) | 7.9 GB Fits | 8.0 GB Fits | 8.7 GB Fits | 11.5 GB Fits | 431 |
| 4-bit (Q4_K_M) | 9.7 GB Fits | 9.8 GB Fits | 10.5 GB Fits | 13.3 GB Fits | 344 |
| 5-bit (Q5_K_M) | 11.1 GB Fits | 11.3 GB Fits | 12.0 GB Fits | 14.8 GB Tight | 295 |
| 6-bit (Q6_K) • | 13.8 GB Tight | 13.9 GB Tight | 14.6 GB Tight | 17.5 GB No | 235 |
| 8-bit (Q8_0) • | 16.3 GB No | 16.4 GB No | 17.1 GB No | 19.9 GB No | — |
| 16-bit (F16/BF16) • | 30.0 GB No | 30.1 GB No | 30.8 GB No | 33.7 GB No | — |
• real GGUF file size from legraphista/DeepSeek-V2-Lite-IMat-GGUF. Speed is a bandwidth ceiling (560 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs DeepSeek V2 Lite: Arc B580 (12 GB, launch MSRP $249) at Q4_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the Arc A770 16GB: gpt-oss 20B (21B, MoE) at Q8_0, about 12.3 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
DeepSeek V2 Lite 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
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (deepseek-ai/DeepSeek-V2-Lite), Intel specs. Model data last checked 2026-11-17; refreshed hourly.