Model benchmarks
glm-4.7-flash-unsloth:small-hotfixed-90kHEAT local LLM performance
As of April 2026, glm-4.7-flash-unsloth:small-hotfixed-90kHEAT runs at up to 75.0 tok/s for local inference (best of 42 community benchmark runs across 1 GPU).
OllamaQ3_K_S
Model size
29.9B
Peak speed
75.0 tok/s
Average speed
39.3 tok/s
Min memory
n/a
Max context
65,536 tokens
Best quality
90.8
Benchmark runs
42
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination glm-4.7-flash-unsloth:small-hotfixed-90kHEAT 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 | Q3_K_S | 75.0 tok/s | 39.3 tok/s | n/a | 65,536 tokens | 62.8 | 42 |
Frequently asked questions
- How fast is glm-4.7-flash-unsloth:small-hotfixed-90kHEAT for local inference?
- Across 42 community benchmark runs, glm-4.7-flash-unsloth:small-hotfixed-90kHEAT reaches up to 75.0 tok/s and averages 39.3 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does glm-4.7-flash-unsloth:small-hotfixed-90kHEAT need?
- The leanest observed configuration used about n/a of memory (quantizations tested: Q3_K_S).
- Which tools have been used to run glm-4.7-flash-unsloth:small-hotfixed-90kHEAT?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.