Model benchmarks
unsloth/gemma-4-E4B-it-GGUF:Q4_K_M local LLM performance
As of October 2026, unsloth/gemma-4-E4B-it-GGUF:Q4_K_M runs at up to 94.7 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
4B
Peak speed
94.7 tok/s
Average speed
93.6 tok/s
Avg PP
1122.2 tok/s
Min memory
7.5 GB
Max context
16,384 tokens
Avg output / run
6,905 tokens
Avg runtime / run
1m 19s
Avg quality
62.7
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 | 62.6 | 62.7 | 62.9 |
| Agent Workflow | 69.7 | 70.6 | 71.5 |
| Code Generation | 48.9 | 50.9 | 52.9 |
| Role Play & Narrative | 65.3 | 69.6 | 74.0 |
| Research & Analysis | 52.0 | 59.8 | 67.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/gemma-4-E4B-it-GGUF:Q4_K_M 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 2080 Ti | llama.cpp | Q4_K_M | 94.7 tok/s | 93.6 tok/s | 7.5 GB | 16,384 tokens | 62.7 | 2 |
Benchmark runs
All 2 unsloth/gemma-4-E4B-it-GGUF:Q4_K_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is unsloth/gemma-4-E4B-it-GGUF:Q4_K_M good for agentic (tool-using) tasks?
- In our benchmarks, unsloth/gemma-4-E4B-it-GGUF:Q4_K_M scores 70.6/100 for agentic workflows. It runs at about 93.6 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~116.8 tok/s) and still scores well for agentic workflows (88.4/100).
- How fast is unsloth/gemma-4-E4B-it-GGUF:Q4_K_M for local inference?
- Across 2 community benchmark runs, unsloth/gemma-4-E4B-it-GGUF:Q4_K_M reaches up to 94.7 tok/s and averages 93.6 tok/s, with the fastest results on NVIDIA GeForce RTX 2080 Ti.
- How much memory does unsloth/gemma-4-E4B-it-GGUF:Q4_K_M need?
- The leanest observed configuration used about 7.5 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run unsloth/gemma-4-E4B-it-GGUF:Q4_K_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.