Skip to content
llm-speed
Leaderboard/RTX 4090/Llama-3.1-8B-Instruct

Can an RTX 4090 run Llama-3.1-8B-Instruct?

llm-speed has not measured Llama-3.1-8B-Instruct on RTX 4090 itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 137.3 tok/s at Q4_K_M 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

QuantRuntimeBuildDecode tok/s (best run)WorkloadRunsSource
Q4_K_Mollama0.31.1137.3chat-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_2np7abzjobe2026-10-14chat-shortQ4_K_Mollama · 0.31.1110256137.3269.1409–Community-submitted
r_2np7abzjobe2026-10-14chat-longQ4_K_Mollama · 0.31.13137376129.24652.7674–Community-submitted
r_2np7abzjobe2026-10-14agent-traceQ4_K_Mollama · 0.31.13210840130.53955.2429–Community-submitted
r_2np7abzjobe2026-10-14concurrent-decodeQ4_K_Mollama · 0.31.11024256136.0–––Community-submitted

Questions

Can an RTX 4090 run Llama-3.1-8B-Instruct?

llm-speed has not measured Llama-3.1-8B-Instruct on RTX 4090 itself yet, so there is no llm-speed verdict. 1 community-submitted run exists (fastest 137.3 tok/s at Q4_K_M on ollama); community-submitted, not measured by llm-speed, so it gives no verdict.

What did community runs measure for Llama-3.1-8B-Instruct on an RTX 4090?

1 community-submitted run (community-submitted, not measured by llm-speed): Q4_K_M on ollama: 137.3 tok/s. They are listed for reference and give no llm-speed verdict.

Sources and related pages