Leaderboard/gemma-4-31B-it-Q4_K_M.gguf/RTX 5090 (32GB)/r__679a-4h44q

gemma-4-31B-it-Q4_K_M.gguf on RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB

Name: gemma-4-31B-it-Q4_K_M.gguf on RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB
Creator: llm-speed
License: https://creativecommons.org/licenses/by/4.0/
Keywords: LLM benchmark, tokens per second, gemma-4-31B-it-Q4_K_M.gguf, RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB, llama.cpp

RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB

suite suite-v1

cli 0.0.3

signed0tv44ISLy1…

Embed badgesubmitted Jul 01, 2026

https://llm-speed.com/r/r__679a-4h44q

Workload results

Workload	Backend	Model	decode tok/s	prefill tok/s	TTFT	p50	p95
chat-short	llama.cpp	gemma-4-31B-it-Q4_K_M.gguf	66.70tok/s	—	179ms	14.9ms	15.1ms

Reproduce on your machine

Same workload, same model, signed at your rig. The exact command that produced this run:

$ pipx install llm-speed && llm-speed bench --model 'gemma-4-31B-it-Q4_K_M.gguf' --workload 'chat-short'

Runs in about a minute. Your number lands on the leaderboard signed and linkable. How it's measured.

Embed this run

Drop the badge into a README, blog post, or signature. Each render is a backlink to the signed result.

[![llm-speed: 66.7 tok/s on RTX 5090 (32GB) (gemma-4-31B-it-Q4_K_M.gguf)](https://llm-speed.com/badge/r__679a-4h44q.svg)](https://llm-speed.com/r/r__679a-4h44q)

Related benchmarks

More gemma-4-31B-it-Q4_K_M.gguf benchmarks — every backend and rig that has run this model.
More RTX 5090 (32GB) LLM benchmarks — every model measured on this hardware.

Provenance

Run ID: r__679a-4h44q
Fingerprint hash: 013ca61a09d17996
Public key: 0tv44ISLy10gz6Oc6FJig3eWJVLwso9oKemSM4nicKM=
Received: 2026-07-01 04:39:36