Can an M3 Ultra run Qwen3-4B-Instruct-2507?
llm-speed has not measured Qwen3-4B-Instruct-2507 on M3 Ultra itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 182.7 tok/s at 4-bit on mlx); 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 |
|---|---|---|---|---|---|---|
| 4-bit | mlx | 0.31.3 | 182.7 | 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_p2rpb_0iyjj | 2026-07-12 | chat-short | 4-bit | mlx · 0.31.3 | 110 | 256 | 182.7 | 636.6 | 173 | – | Community-submitted |
| r_p2rpb_0iyjj | 2026-07-12 | chat-long | 4-bit | mlx · 0.31.3 | 3147 | 567 | 147.0 | 1913.7 | 1644 | – | Community-submitted |
| r_p2rpb_0iyjj | 2026-07-12 | agent-trace | 4-bit | mlx · 0.31.3 | 3247 | 840 | 160.8 | 1913.6 | 1091 | – | Community-submitted |
| r_p2rpb_0iyjj | 2026-07-12 | concurrent-decode | 4-bit | mlx · 0.31.3 | 1024 | 256 | 168.4 | – | – | – | Community-submitted |
Questions
Can an M3 Ultra run Qwen3-4B-Instruct-2507?
llm-speed has not measured Qwen3-4B-Instruct-2507 on M3 Ultra itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 182.7 tok/s at 4-bit on mlx); community-submitted, not measured by llm-speed, so it gives no verdict.
What did community runs measure for Qwen3-4B-Instruct-2507 on an M3 Ultra?
1 community-submitted run (community-submitted, not measured by llm-speed): 4-bit on mlx: 182.7 tok/s. They are listed for reference and give no llm-speed verdict.