Model benchmarks
unsloth/gemma-4-E4B-it-qat-GGUF local LLM performance
As of October 2026, unsloth/gemma-4-E4B-it-qat-GGUF runs at up to 205.4 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
4B
Peak speed
205.4 tok/s
Average speed
176.2 tok/s
Avg PP
2833.0 tok/s
Min memory
4.5 GB
Max context
8,192 tokens
Avg output / run
9,845 tokens
Avg runtime / run
1m
Avg quality
67.0
Benchmark runs
3
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 3 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 | 64.1 | 67.0 | 71.1 |
| Agent Workflow | 72.6 | 79.3 | 85.3 |
| Code Generation | 41.9 | 50.7 | 56.6 |
| Role Play & Narrative | 71.6 | 74.1 | 76.6 |
| Research & Analysis | 53.4 | 63.8 | 71.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/gemma-4-E4B-it-qat-GGUF 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3070 Ti | Unsloth Studio | UD-Q4_K_XL | 205.4 tok/s | 176.2 tok/s | 4.5 GB | 8,192 tokens | 67.0 | 3 |
Benchmark runs
All 3 unsloth/gemma-4-E4B-it-qat-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is unsloth/gemma-4-E4B-it-qat-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, unsloth/gemma-4-E4B-it-qat-GGUF scores 79.3/100 for agentic workflows. It runs at about 176.2 tok/s, so if you want more speed, unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M is faster (~246.8 tok/s) and still scores well for agentic workflows (80.6/100).
- How fast is unsloth/gemma-4-E4B-it-qat-GGUF for local inference?
- Across 3 community benchmark runs, unsloth/gemma-4-E4B-it-qat-GGUF reaches up to 205.4 tok/s and averages 176.2 tok/s, with the fastest results on NVIDIA GeForce RTX 3070 Ti.
- How much memory does unsloth/gemma-4-E4B-it-qat-GGUF need?
- The leanest observed configuration used about 4.5 GB of memory (quantizations tested: UD-Q4_K_XL).
- Which tools have been used to run unsloth/gemma-4-E4B-it-qat-GGUF?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.