Skip to content
llm-speed

glm-4.7-flash on RTX 4090 (24GB) + AMD EPYC 75F3 32-Core Processor (64c) + 504GB

Workload results

WorkloadBackendModeldecode tok/sprefill tok/sTTFTp50p95
chat-shortollama@0.31.1glm-4.7-flashQ4_K_M
chat-longollama@0.31.1glm-4.7-flashQ4_K_M
concurrent-decodeollama@0.31.1glm-4.7-flashQ4_K_M
agent-traceollama@0.31.1glm-4.7-flashQ4_K_M129.9tok/s2,491.1tok/s1,262ms6.2ms11.5ms

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 'glm-4.7-flash' --workload 'agent-trace'

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: 130 tok/s on RTX 4090 (24GB) (glm-4.7-flash)
[![llm-speed: 130 tok/s on RTX 4090 (24GB) (glm-4.7-flash)](https://llm-speed.com/badge/r_o636l3cc-rr.svg)](https://llm-speed.com/r/r_o636l3cc-rr)

Related benchmarks

Provenance

Run ID
r_o636l3cc-rr
Fingerprint hash
Public key
BsJd7kJbLQjLlxdpBoKhCM7QlJ7qUzp2zJVk6uVa7s0=
Received
2026-07-08 01:27:33