Skip to content
llm-speed
Leaderboard/M3 Ultra/Qwen2.5-Coder-32B-Instruct

Can an M3 Ultra run Qwen2.5-Coder-32B-Instruct?

llm-speed has not measured Qwen2.5-Coder-32B-Instruct on M3 Ultra itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 34.5 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

QuantRuntimeBuildDecode tok/s (best run)WorkloadRunsSource
4-bitmlx0.31.334.5chat-short1Community-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.

VRAM: not recorded for these runs. The VRAM calculator gives an estimate (predicted, not measured).

Every measured row

RunDate (UTC)WorkloadQuantRuntime / buildPrompt tokensOutput tokensDecode tok/sPrefill tok/sTTFT msVRAM GiBSource
r_721b4bls_oq2026-04-28chat-short4-bitmlx · 0.31.313125634.5144.1909–Community-submitted

Questions

Can an M3 Ultra run Qwen2.5-Coder-32B-Instruct?

llm-speed has not measured Qwen2.5-Coder-32B-Instruct on M3 Ultra itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 34.5 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 Qwen2.5-Coder-32B-Instruct on an M3 Ultra?

1 community-submitted run (community-submitted, not measured by llm-speed): 4-bit on mlx: 34.5 tok/s. They are listed for reference and give no llm-speed verdict.

Sources and related pages