Intel Arc B580 12GBBudget pickC51.3 tok/s decode
~$249 MSRP
Can it run?
Too heavy
Using Q4_K_M in Ollama
Fit status
Too heavy
Decode
18.9 tok/s
TTFT
10251 ms
Safe context
9K
Memory
7.0 GB / 4.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | F | Too heavy | 12.9 tok/s | 21910 ms | 16K |
| Chat | F | Too heavy | 12.9 tok/s | 8216 ms | 5K |
| Coding | F | Too heavy | 18.9 tok/s | 10251 ms | 9K |
| RAG | F | Too heavy | 12.9 tok/s | 27388 ms | 16K |
| Reasoning | F | Too heavy | 12.9 tok/s | 17802 ms | 9K |
How Mistral 7B Instruct v0.2 (7B params) fits at each quantization level on Intel Arc A370M 4GB (4.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 2.7 GB | Low | C44 |
Q3_K_S | 3 | 3.4 GB | Low | C44 |
NVFP4 | 4 |
Upgrade options
Intel Arc B580 12GBBudget pick~$249 MSRP
~$269 MSRP
RTX 2080 Ti 11GBBiggest leap~$999 MSRP
Intel Arc B570 10GBIntel upgrade| Medium |
| C44 |
Q4_K_M | 4 | 4.3 GB | Medium | F0 |
Q5_K_M | 5 | 5.0 GB | High | F0 |
Q6_K | 6 | 5.7 GB | High | F0 |
Q8_0 | 8 | 7.5 GB | Very High | F0 |
F16 | 16 | 14.3 GB | Maximum | F0 |