Model benchmarks
unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL local LLM performance
As of October 2026, unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL runs at up to 31.7 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
31B
Peak speed
31.7 tok/s
Average speed
31.1 tok/s
Avg PP
355.5 tok/s
Min memory
25.8 GB
Max context
131,072 tokens
Avg output / run
10,217 tokens
Avg runtime / run
5m 29s
Avg quality
74.1
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 | 71.4 | 74.1 | 76.9 |
| Agent Workflow | 76.7 | 77.8 | 78.8 |
| Code Generation | 64.2 | 69.2 | 74.2 |
| Role Play & Narrative | 70.6 | 75.6 | 80.5 |
| Research & Analysis | 73.9 | 73.9 | 74.0 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Advanced Micro Devices, Inc. [AMD/ATI] Device 7551 | llama.cpp | Q4_K | 31.7 tok/s | 31.1 tok/s | 25.8 GB | 131,072 tokens | 74.1 | 2 |
Benchmark runs
All 2 unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL good for coding?
- In our benchmarks, unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL scores 69.2/100 for coding. It runs at about 31.1 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 unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL good for agentic (tool-using) tasks?
- In our benchmarks, unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL scores 77.8/100 for agentic workflows. It runs at about 31.1 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 unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL for local inference?
- Across 2 community benchmark runs, unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL reaches up to 31.7 tok/s and averages 31.1 tok/s, with the fastest results on Advanced Micro Devices, Inc. [AMD/ATI] Device 7551.
- How much memory does unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL need?
- The leanest observed configuration used about 25.8 GB of memory (quantizations tested: Q4_K).
- Which tools have been used to run unsloth/gemma-4-31B-it-GGUF:UD-Q4_K_XL?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.