Skip to content
llm-speed
Leaderboard/RTX 5090/Qwen2.5-Coder-14B-Instruct

Can an RTX 5090 run Qwen2.5-Coder-14B-Instruct?

Yes: an RTX 5090 runs Qwen2.5-Coder 14B at 137.3 tok/s at Q4_K_M, measured on llama.cpp with a 131-token prompt in October 2026.

3 signed runs on llm-speed. Single-request decode speed in tokens per second; the short-chat workload unless noted. 1 of 3 runs were measured by llm-speed (@llmspeed); the other 2 are community-submitted (signed on the submitter's own machine, not measured by llm-speed, and not used for llm-speed verdicts). Runs measured by llm-speed are credited to @llmspeed. 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 1268eda137.3chat-short1Measured by llm-speed@llmspeed
not reportedllama.cppnot reported140.0chat-short2Community-submitted

Fastest quant that fits: Q4_K_M on llama.cpp, 137.3 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_opuj21f13-_2026-07-01chat-short–llama.cpp · not reported0256140.0–42–Community-submitted
r_xnr_k4emoyr2026-10-17chat-shortQ4_K_Mllama.cpp · commit 1268eda131256137.32016.965–Measured by llm-speed@llmspeed
r_p_f63tcgans2026-07-01chat-short–llama.cpp · not reported0256136.0–51–Community-submitted
r_xnr_k4emoyr2026-10-17chat-longQ4_K_Mllama.cpp · commit 1268eda3168564128.95987.2529–Measured by llm-speed@llmspeed
r_opuj21f13-_2026-07-01chat-long–llama.cpp · not reported0518123.0–457–Community-submitted
r_opuj21f13-_2026-07-01agent-trace–llama.cpp · not reported3362840130.521985.9104–Community-submitted
r_xnr_k4emoyr2026-10-17agent-traceQ4_K_Mllama.cpp · commit 1268eda3268840128.218881.9113–Measured by llm-speed@llmspeed
r_xnr_k4emoyr2026-10-17concurrent-decodeQ4_K_Mllama.cpp · commit 1268eda1024256136.7–––Measured by llm-speed@llmspeed
r_opuj21f13-_2026-07-01concurrent-decode–llama.cpp · not reported1024256133.8–––Community-submitted

Questions

Can an RTX 5090 run Qwen2.5-Coder-14B-Instruct?

Yes: an RTX 5090 runs Qwen2.5-Coder 14B at 137.3 tok/s at Q4_K_M, measured on llama.cpp with a 131-token prompt in October 2026.

How many tokens per second does Qwen2.5-Coder-14B-Instruct get on an RTX 5090?

Decode speed measured by llm-speed, by quantization and runtime: Q4_K_M on llama.cpp: 137.3 tok/s. Based on 1 run measured by llm-speed; single-request chat-short unless noted. 2 community-submitted runs are listed on the page, labelled, and not counted here.

What is the fastest quant of Qwen2.5-Coder-14B-Instruct that fits on an RTX 5090?

Q4_K_M on llama.cpp was the fastest measured setting at 137.3 tok/s; it fit because it ran. Other quants are listed only where a run measured them.

How much VRAM does Qwen2.5-Coder-14B-Instruct use on an RTX 5090?

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

Sources and related pages