Model benchmarks
glm-4.7-flash:latest local LLM performance
As of April 2026, glm-4.7-flash:latest runs at up to 37.5 tok/s for local inference (best of 5 community benchmark runs across 1 GPU).
OllamaQ4_K_M
Model size
29.9B
Peak speed
37.5 tok/s
Average speed
19.9 tok/s
Min memory
18.6 GB
Max context
7,615 tokens
Best quality
90.9
Benchmark runs
5
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.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XTX | Ollama | Q4_K_M | 37.5 tok/s | 19.9 tok/s | 18.6 GB | 7,615 tokens | 66.9 | 5 |
Frequently asked questions
- How fast is glm-4.7-flash:latest for local inference?
- Across 5 community benchmark runs, glm-4.7-flash:latest reaches up to 37.5 tok/s and averages 19.9 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 18.6 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run glm-4.7-flash:latest?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.