Skip to content
llm-speed
Leaderboard/models/glm-4-7-flash

glm-4.7-flash

4 workload results across 1 hardware configuration.

Fastest local config

129.9 decode tok/s

on RTX 4090 (24GB) + AMD EPYC 75F3 32-Core Processor (64c) + 504GB via ollama (Q4_K_M) — see full run

Local runs (4 runs)

Runs from contributors' own machines via MLX, llama.cpp, vLLM, exllamav2, or ollama. Signed on the submitter's hardware.

RTX 4090 (24GB) + AMD EPYC 75F3 32-Core Processor (64c) + 504GBRTX 4090 (24GB) + AMD EPYC 75F3 32-Core Processor (64c) + 504GB

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortollama@0.31.1Q4_K_Mno datano datano datar_o636l3cc-rr
chat-longollama@0.31.1Q4_K_Mno datano datano datar_o636l3cc-rr
concurrent-decodeollama@0.31.1Q4_K_Mno datano datano datar_o636l3cc-rr
agent-traceollama@0.31.1Q4_K_M129.9tok/s2,491.1tok/s1,262msr_o636l3cc-rr

glm-4.7-flash on hardware