Model benchmarks
unsloth/gemma-3-1b-it-GGUF local LLM performance
As of November 2026, unsloth/gemma-3-1b-it-GGUF runs at up to 39.8 tok/s for local inference (best of 5 community benchmark runs across 1 GPU).
Model size
1B
Peak speed
39.8 tok/s
Average speed
33.8 tok/s
Avg PP
634.6 tok/s
Min memory
2.2 GB
Max context
65,536 tokens
Avg output / run
4,819 tokens
Avg runtime / run
2m 29s
Avg quality
34.8
Benchmark runs
5
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 5 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 | 28.7 | 34.8 | 40.3 |
| Agent Workflow | 35.6 | 48.0 | 63.4 |
| Code Generation | 1.9 | 5.8 | 11.3 |
| Role Play & Narrative | 45.5 | 58.5 | 69.5 |
| Research & Analysis | 20.9 | 26.9 | 34.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/gemma-3-1b-it-GGUF 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon Vega Series / Radeon Vega Mobile Series | Unsloth Studio | UD-Q4_K_XL | 39.8 tok/s | 38.9 tok/s | 2.2 GB | 65,536 tokens | 29.9 | 2 |
| AMD Radeon Vega Series / Radeon Vega Mobile Series | Unsloth Studio | Q8_0 | 31.5 tok/s | 30.4 tok/s | 2.4 GB | 32,768 tokens | 38.1 | 3 |
Benchmark runs
All 5 unsloth/gemma-3-1b-it-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is unsloth/gemma-3-1b-it-GGUF good for coding?
- In our benchmarks, unsloth/gemma-3-1b-it-GGUF scores 5.8/100 for coding. It runs at about 33.8 tok/s, so if you want more speed, Huihui-Qwen3.8-27B-abliterated-Swift-1.5-GSQ-RCO-IQ3_S-mtp is faster (~43.5 tok/s) and still scores well for coding (86.6/100).
- Is unsloth/gemma-3-1b-it-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, unsloth/gemma-3-1b-it-GGUF scores 48.0/100 for agentic workflows. It runs at about 33.8 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 unsloth/gemma-3-1b-it-GGUF for local inference?
- Across 5 community benchmark runs, unsloth/gemma-3-1b-it-GGUF reaches up to 39.8 tok/s and averages 33.8 tok/s, with the fastest results on AMD Radeon Vega Series / Radeon Vega Mobile Series.
- How much memory does unsloth/gemma-3-1b-it-GGUF need?
- The leanest observed configuration used about 2.2 GB of memory (quantizations tested: Q8_0, UD-Q4_K_XL).
- Which tools have been used to run unsloth/gemma-3-1b-it-GGUF?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.