Skip to content
llm-speed
Leaderboard/RTX 4090/Qwen3-Coder-30B-A3B-Instruct

Can an RTX 4090 run Qwen3-Coder-30B-A3B-Instruct?

llm-speed has not measured Qwen3-Coder-30B-A3B-Instruct on RTX 4090 itself yet, so there is no llm-speed verdict. 2 community-submitted runs exist (fastest 232.5 tok/s at Q4_K_M on llama.cpp); community-submitted, not measured by llm-speed, so they give no verdict.

2 signed runs on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. All 2 runs are 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_Mllama.cppcommit df18bee232.5chat-short1Community-submitted
Q4_K_Mollama0.31.1145.2chat-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_1k8942tw3zf2026-10-14chat-shortQ4_K_Mllama.cpp · commit df18bee110256232.5831.9132–Community-submitted
r_wjq32z47vlp2026-07-02chat-shortQ4_K_Mollama · 0.31.1110256145.2195.6562–Community-submitted
r_1k8942tw3zf2026-10-14chat-longQ4_K_Mllama.cpp · commit df18bee3147561206.97688.7409–Community-submitted
r_wjq32z47vlp2026-07-02chat-longQ4_K_Mollama · 0.31.13147535165.53527.2892–Community-submitted
r_1k8942tw3zf2026-10-14agent-traceQ4_K_Mllama.cpp · commit df18bee3247840216.419138.1108–Community-submitted
r_1k8942tw3zf2026-10-14concurrent-decodeQ4_K_Mllama.cpp · commit df18bee1024256225.1–––Community-submitted
r_wjq32z47vlp2026-07-02concurrent-decodeQ4_K_Mollama · 0.31.11024256179.9–––Community-submitted

Questions

Can an RTX 4090 run Qwen3-Coder-30B-A3B-Instruct?

llm-speed has not measured Qwen3-Coder-30B-A3B-Instruct on RTX 4090 itself yet, so there is no llm-speed verdict. 2 community-submitted runs exist (fastest 232.5 tok/s at Q4_K_M on llama.cpp); community-submitted, not measured by llm-speed, so they give no verdict.

What did community runs measure for Qwen3-Coder-30B-A3B-Instruct on an RTX 4090?

2 community-submitted runs (community-submitted, not measured by llm-speed): Q4_K_M on llama.cpp: 232.5 tok/s; Q4_K_M on ollama: 145.2 tok/s. They are listed for reference and give no llm-speed verdict.

Sources and related pages