Can Llama 3.2 3B Instruct run on the Arc B580?
Yes. At 8K context the best fit is Q8_0, using about 4.7 GB of the 11.4 GB usable on the Arc B580. Estimated speed ceiling: ~133 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) • | 2.4 GB Fits | 2.8 GB Fits | 5.4 GB Fits | 15.9 GB No | 334 |
| 3-bit (Q3_K_M) • | 2.7 GB Fits | 3.1 GB Fits | 5.7 GB Fits | 16.2 GB No | 270 |
| 4-bit (Q4_K_M) • | 3.0 GB Fits | 3.4 GB Fits | 6.0 GB Fits | 16.5 GB No | 226 |
| 5-bit (Q5_K_M) • | 3.2 GB Fits | 3.7 GB Fits | 6.3 GB Fits | 16.8 GB No | 196 |
| 6-bit (Q6_K) • | 3.5 GB Fits | 4.0 GB Fits | 6.6 GB Fits | 17.1 GB No | 172 |
| 8-bit (Q8_0) • | 4.3 GB Fits | 4.7 GB Fits | 7.3 GB Fits | 17.8 GB No | 133 |
| 16-bit (F16/BF16) • | 13.1 GB No | 13.5 GB No | 16.1 GB No | 26.6 GB No | — |
• real GGUF file size from unsloth/Llama-3.2-3B-Instruct-GGUF. Speed is a bandwidth ceiling (456 GB/s), not a benchmark. Methodology.
More
Llama 3.2 3B Instruct on every GPU and Mac · Every model that runs on the Arc B580 · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (meta-llama/Llama-3.2-3B-Instruct), Intel specs. Data as of 2026-11-17.