Leaderboard/RTX 5090/Llama-3.1-8B-Instruct

Can an RTX 5090 run Llama-3.1-8B-Instruct?

llm-speed has not measured Llama-3.1-8B-Instruct on RTX 5090 itself yet, so there is no llm-speed verdict. 2 community-submitted runs exist (fastest 232.2 tok/s at an unreported quant 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

Quant	Runtime	Build	Decode tok/s (best run)	Workload	Runs	Source
not reported	llama.cpp	not reported	232.2	chat-short	2	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_kfrkg-vn376	2026-07-01	chat-short	–	llama.cpp · not reported	0	256	232.2	–	34	–	Community-submitted
r_qr4srge34da	2026-07-01	chat-short	–	llama.cpp · not reported	0	256	229.4	–	36	–	Community-submitted
r_qr4srge34da	2026-07-01	chat-long	–	llama.cpp · not reported	0	351	211.4	–	266	–	Community-submitted
r_qr4srge34da	2026-07-01	agent-trace	–	llama.cpp · not reported	3362	840	210.3	36720.3	61	–	Community-submitted
r_qr4srge34da	2026-07-01	concurrent-decode	–	llama.cpp · not reported	1024	256	223.0	–	–	–	Community-submitted

Questions