Model benchmarks
GLM-4.7-Flash-REAP_t02p95k50m01D11 local LLM performance
As of November 2026, GLM-4.7-Flash-REAP_t02p95k50m01D11 runs at up to 49.7 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
49.7 tok/s
Average speed
49.7 tok/s
Avg PP
1061.2 tok/s
Min memory
51.1 GB
Max context
32,768 tokens
Avg output / run
14,687 tokens
Avg runtime / run
5m 6s
Avg quality
65.6
Benchmark runs
2
GPUs tested
1
Quality by task
Average LLM-judged quality (0–100) with the run-to-run spread shown as a P5–P95 band, overall and for each benchmark task, across all 2 runs. The low and high columns show how much the judge’s score varies between runs, and need at least two runs to display.
| Task | P5 (low) | Avg | P95 (high) |
|---|---|---|---|
| Overall | 63.5 | 65.6 | 67.7 |
| Agent Workflow | 72.7 | 76.8 | 80.9 |
| Code Generation | 38.4 | 45.9 | 53.4 |
| Role Play & Narrative | 70.3 | 74.3 | 78.3 |
| Research & Analysis | 64.5 | 65.5 | 66.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination GLM-4.7-Flash-REAP_t02p95k50m01D11 has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Tesla V100-PCIE-32GB | llama.cpp | — | 49.7 tok/s | 49.7 tok/s | 51.1 GB | 32,768 tokens | 65.6 | 2 |
Benchmark runs
All 2 GLM-4.7-Flash-REAP_t02p95k50m01D11 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is GLM-4.7-Flash-REAP_t02p95k50m01D11 good for coding?
- In our benchmarks, GLM-4.7-Flash-REAP_t02p95k50m01D11 scores 45.9/100 for coding. It runs at about 49.7 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is GLM-4.7-Flash-REAP_t02p95k50m01D11 good for agentic (tool-using) tasks?
- In our benchmarks, GLM-4.7-Flash-REAP_t02p95k50m01D11 scores 76.8/100 for agentic workflows. It runs at about 49.7 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is GLM-4.7-Flash-REAP_t02p95k50m01D11 for local inference?
- Across 2 community benchmark runs, GLM-4.7-Flash-REAP_t02p95k50m01D11 reaches up to 49.7 tok/s and averages 49.7 tok/s, with the fastest results on Tesla V100-PCIE-32GB.
- How much memory does GLM-4.7-Flash-REAP_t02p95k50m01D11 need?
- The leanest observed configuration used about 51.1 GB of memory.
- Which tools have been used to run GLM-4.7-Flash-REAP_t02p95k50m01D11?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.