Model benchmarks

glm-4.7-flash:latest local LLM performance

As of April 2026, glm-4.7-flash:latest runs at up to 46.1 tok/s for local inference (best of 8 community benchmark runs across 1 GPU).

LM StudioOllamaQ4_K_M

Model size

29.9B

Peak speed

46.1 tok/s

Average speed

29.6 tok/s

Min memory

n/a

Max context

32,768 tokens

Best quality

90.9

Benchmark runs

8

GPUs tested

1

Performance by hardware and tool

Every hardware/tool/quantization combination glm-4.7-flash:latest has been benchmarked on, ranked by peak token generation speed. Last updated April 2026.

HardwareToolQuantBest tok/sAvg tok/sMemoryContextQualityRuns
AMD Radeon RX 7900 XTXLM Studio46.1 tok/s45.6 tok/sn/a32,768 tokens47.43
AMD Radeon RX 7900 XTXOllamaQ4_K_M37.5 tok/s19.9 tok/s18.6 GB7,615 tokens66.95

Frequently asked questions

How fast is glm-4.7-flash:latest for local inference?
Across 8 community benchmark runs, glm-4.7-flash:latest reaches up to 46.1 tok/s and averages 29.6 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
How much memory does glm-4.7-flash:latest need?
The leanest observed configuration used about n/a of memory (quantizations tested: Q4_K_M).
Which tools have been used to run glm-4.7-flash:latest?
Benchmarks were submitted using LM Studio, Ollama. Results are community-contributed and updated as new runs arrive.