Skip to content
llm-speed
Leaderboard/RTX 3090/Qwen3-Coder-30B-A3B-Instruct

Can an RTX 3090 run Qwen3-Coder-30B-A3B-Instruct?

Yes: an RTX 3090 runs Qwen3-Coder 30B-A3B at 199.7 tok/s at Q4_K_M, measured on llama.cpp with a 110-token prompt in October 2026.

1 signed run on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. This run was measured by llm-speed (@llmspeed). Runs measured by llm-speed are credited to @llmspeed.

Measured tok/s by quant and runtime

QuantRuntimeBuildDecode tok/s (best run)WorkloadRunsSource
Q4_K_Mllama.cppcommit ea0c4c2199.7chat-short1Measured by llm-speed@llmspeed

Fastest quant that fits: Q4_K_M on llama.cpp, 199.7 tok/s (measured by llm-speed; it fits because it ran on this hardware). Quants without a run are not listed.

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_0dh1kzbv4h02026-10-17chat-shortQ4_K_Mllama.cpp · commit ea0c4c2110256199.7612.5180–Measured by llm-speed@llmspeed
r_0dh1kzbv4h02026-10-17chat-longQ4_K_Mllama.cpp · commit ea0c4c23147580187.03971.3792–Measured by llm-speed@llmspeed
r_0dh1kzbv4h02026-10-17agent-traceQ4_K_Mllama.cpp · commit ea0c4c23247840190.910182.2214–Measured by llm-speed@llmspeed
r_0dh1kzbv4h02026-10-17concurrent-decodeQ4_K_Mllama.cpp · commit ea0c4c21024256198.0–––Measured by llm-speed@llmspeed

Questions

Can an RTX 3090 run Qwen3-Coder-30B-A3B-Instruct?

Yes: an RTX 3090 runs Qwen3-Coder 30B-A3B at 199.7 tok/s at Q4_K_M, measured on llama.cpp with a 110-token prompt in October 2026.

How many tokens per second does Qwen3-Coder-30B-A3B-Instruct get on an RTX 3090?

Decode speed measured by llm-speed, by quantization and runtime: Q4_K_M on llama.cpp: 199.7 tok/s. Based on 1 run measured by llm-speed; single-request chat-short unless noted.

What is the fastest quant of Qwen3-Coder-30B-A3B-Instruct that fits on an RTX 3090?

Q4_K_M on llama.cpp was the fastest measured setting at 199.7 tok/s; it fit because it ran. Other quants are listed only where a run measured them.

How much VRAM does Qwen3-Coder-30B-A3B-Instruct use on an RTX 3090?

Memory use was not recorded for these runs. The VRAM calculator gives an estimate, not a measurement.

Sources and related pages