Can an M1 Pro run Llama 3.2 1B?
llm-speed has not measured Llama 3.2 1B on M1 Pro itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 103.1 tok/s at Q8_0 on ollama); community-submitted, not measured by llm-speed, so it gives no verdict.
1 signed run on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. This run is community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts). Verdicts and headline numbers use only llm-speed's own runs and fit tests.
Measured tok/s by quant and runtime
| Quant | Runtime | Build | Decode tok/s (best run) | Workload | Runs | Source |
|---|---|---|---|---|---|---|
| Q8_0 | ollama | 0.32.14 | 103.1 | chat-short | 1 | Community-submitted |
llm-speed has not measured this pair itself, so there is no llm-speed verdict or fastest quant. The rows above are community-submitted, not measured by llm-speed.
Every measured row
| Run | Date (UTC) | Workload | Quant | Runtime / build | Prompt tokens | Output tokens | Decode tok/s | Prefill tok/s | TTFT ms | VRAM GiB | Source |
|---|---|---|---|---|---|---|---|---|---|---|---|
| r_w-p7v--eync | 2026-08-18 | chat-short | Q8_0 | ollama · 0.32.14 | 125 | 256 | 103.1 | 8.8 | 14247 | – | Community-submitted |
| r_w-p7v--eync | 2026-08-18 | chat-long | Q8_0 | ollama · 0.32.14 | 3152 | 413 | 81.3 | 1246.5 | 2529 | – | Community-submitted |
| r_w-p7v--eync | 2026-08-18 | agent-trace | Q8_0 | ollama · 0.32.14 | 3225 | 840 | 93.1 | 2975.3 | 516 | – | Community-submitted |
| r_w-p7v--eync | 2026-08-18 | concurrent-decode | Q8_0 | ollama · 0.32.14 | 1024 | 256 | 97.3 | – | – | – | Community-submitted |
Questions
Can an M1 Pro run Llama 3.2 1B?
llm-speed has not measured Llama 3.2 1B on M1 Pro itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 103.1 tok/s at Q8_0 on ollama); community-submitted, not measured by llm-speed, so it gives no verdict.
What did community runs measure for Llama 3.2 1B on an M1 Pro?
1 community-submitted run (community-submitted, not measured by llm-speed): Q8_0 on ollama: 103.1 tok/s. They are listed for reference and give no llm-speed verdict.