Model benchmarks
granite-4.2-8b-Q4_K_L local LLM performance
As of September 2026, granite-4.2-8b-Q4_K_L runs at up to 82.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
8B
Peak speed
82.9 tok/s
Average speed
71.6 tok/s
Avg PP
1542.1 tok/s
Min memory
n/a
Max context
131,072 tokens
Avg output / run
22,115 tokens
Avg runtime / run
5m 26s
Avg quality
70.4
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 | 69.0 | 70.4 | 71.9 |
| Agent Workflow | 91.9 | 92.9 | 93.8 |
| Code Generation | 38.1 | 38.2 | 38.3 |
| Role Play & Narrative | 74.0 | 81.2 | 88.3 |
| Research & Analysis | 69.0 | 69.5 | 70.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination granite-4.2-8b-Q4_K_L has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5060 | llama.cpp | Q4_K | 82.9 tok/s | 71.6 tok/s | n/a | 131,072 tokens | 70.4 | 2 |
Benchmark runs
All 2 granite-4.2-8b-Q4_K_L runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is granite-4.2-8b-Q4_K_L good for coding?
- In our benchmarks, granite-4.2-8b-Q4_K_L scores 38.2/100 for coding. It runs at about 71.6 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~90.8 tok/s) and still scores well for coding (83.8/100).
- Is granite-4.2-8b-Q4_K_L good for agentic (tool-using) tasks?
- In our benchmarks, granite-4.2-8b-Q4_K_L scores 92.9/100 for agentic workflows. It runs at about 71.6 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is granite-4.2-8b-Q4_K_L for local inference?
- Across 2 community benchmark runs, granite-4.2-8b-Q4_K_L reaches up to 82.9 tok/s and averages 71.6 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- Which tools have been used to run granite-4.2-8b-Q4_K_L?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.