Model benchmarks
gemma4-it-e4b-FLM:latest local LLM performance
As of August 2026, gemma4-it-e4b-FLM:latest runs at up to 11.6 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
4B
Peak speed
11.6 tok/s
Average speed
5.8 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
7,088 tokens
Avg runtime / run
10m 41s
Avg quality
61.2
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 | 60.9 | 61.2 | 61.6 |
| Agent Workflow | 74.7 | 77.4 | 80.2 |
| Code Generation | 39.5 | 42.4 | 45.2 |
| Role Play & Narrative | 61.6 | 64.1 | 66.6 |
| Research & Analysis | 57.0 | 61.1 | 65.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination gemma4-it-e4b-FLM:latest has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon 880M / 890M | Ollama | — | 11.6 tok/s | 5.8 tok/s | n/a | 65,536 tokens | 61.2 | 2 |
Frequently asked questions
- Is gemma4-it-e4b-FLM:latest good for coding?
- In our benchmarks, gemma4-it-e4b-FLM:latest scores 42.4/100 for coding. It runs at about 5.8 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for coding (66.9/100).
- Is gemma4-it-e4b-FLM:latest good for agentic (tool-using) tasks?
- In our benchmarks, gemma4-it-e4b-FLM:latest scores 77.4/100 for agentic workflows. It runs at about 5.8 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for agentic workflows (71.7/100).
- How fast is gemma4-it-e4b-FLM:latest for local inference?
- Across 2 community benchmark runs, gemma4-it-e4b-FLM:latest reaches up to 11.6 tok/s and averages 5.8 tok/s, with the fastest results on AMD Radeon 880M / 890M.
- How much memory does gemma4-it-e4b-FLM:latest need?
- The leanest observed configuration used about n/a of memory.
- Which tools have been used to run gemma4-it-e4b-FLM:latest?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.