Leaderboard/RTX 3090/DeepSeek-Coder-V2-Lite-Instruct

Can an RTX 3090 run DeepSeek-Coder-V2-Lite-Instruct?

llm-speed has not measured DeepSeek-Coder-V2-Lite-Instruct on RTX 3090 itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 189.5 tok/s at Q4_0 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

Quant	Runtime	Build	Decode tok/s (best run)	Workload	Runs	Source
Q4_0	ollama	0.31.1	189.5	chat-short	1	Community-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

Run	Date (UTC)	Workload	Quant	Runtime / build	Prompt tokens	Output tokens	Decode tok/s	Prefill tok/s	TTFT ms	VRAM GiB	Source
r_o2-1w665rtq	2026-07-02	chat-short	Q4_0	ollama · 0.31.1	117	256	189.5	159.2	735	–	Community-submitted
r_o2-1w665rtq	2026-07-02	chat-long	Q4_0	ollama · 0.31.1	3276	719	77.6	3907.5	838	–	Community-submitted
r_o2-1w665rtq	2026-07-02	agent-trace	Q4_0	ollama · 0.31.1	4077	840	101.2	6933.1	352	–	Community-submitted
r_o2-1w665rtq	2026-07-02	concurrent-decode	Q4_0	ollama · 0.31.1	1024	256	155.6	–	–	–	Community-submitted

Questions