Skip to content
llm-speed
Leaderboard/RTX 3090/Qwen2.5-Coder-7B-Instruct

Can an RTX 3090 run Qwen2.5-Coder-7B-Instruct?

llm-speed has not measured Qwen2.5-Coder-7B-Instruct on RTX 3090 itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 39.9 tok/s at Q4_K_M 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

QuantRuntimeBuildDecode tok/s (best run)WorkloadRunsSource
Q4_K_Mollama0.31.139.9chat-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_pb0jpnbujji2026-07-02chat-shortQ4_K_Mollama · 0.31.113125639.92.846337–Community-submitted
r_pb0jpnbujji2026-07-02chat-longQ4_K_Mollama · 0.31.13168412135.03319.4954–Community-submitted
r_pb0jpnbujji2026-07-02agent-traceQ4_K_Mollama · 0.31.13268840134.24111.1487–Community-submitted
r_pb0jpnbujji2026-07-02concurrent-decodeQ4_K_Mollama · 0.31.11024256139.2–––Community-submitted

Questions

Can an RTX 3090 run Qwen2.5-Coder-7B-Instruct?

llm-speed has not measured Qwen2.5-Coder-7B-Instruct on RTX 3090 itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 39.9 tok/s at Q4_K_M on ollama); community-submitted, not measured by llm-speed, so it gives no verdict.

What did community runs measure for Qwen2.5-Coder-7B-Instruct on an RTX 3090?

1 community-submitted run (community-submitted, not measured by llm-speed): Q4_K_M on ollama: 39.9 tok/s. They are listed for reference and give no llm-speed verdict.

Sources and related pages