Model benchmarks
hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S local LLM performance
As of November 2026, hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S runs at up to 71.4 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
25.2B
Peak speed
71.4 tok/s
Average speed
71.2 tok/s
Avg PP
1231.8 tok/s
Min memory
10.9 GB
Max context
32,768 tokens
Avg output / run
16,478 tokens
Avg runtime / run
4m 1s
Avg quality
71.5
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 | 67.0 | 71.5 | 76.2 |
| Agent Workflow | 74.8 | 76.0 | 77.8 |
| Code Generation | 63.1 | 69.4 | 73.6 |
| Role Play & Narrative | 72.7 | 73.5 | 74.4 |
| Research & Analysis | 55.7 | 67.0 | 80.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S 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 |
|---|---|---|---|---|---|---|---|---|
| Advanced Micro Devices, Inc. [AMD/ATI] Device 7590 | Ollama | IQ3_S | 71.4 tok/s | 71.2 tok/s | 10.9 GB | 32,768 tokens | 71.5 | 3 |
Benchmark runs
All 3 hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S good for coding?
- In our benchmarks, hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S scores 69.4/100 for coding. It runs at about 71.2 tok/s, so if you want more speed, qwen3.8-27b-Swift1.5-Uncensored-ATX-AI3 is faster (~85.5 tok/s) and still scores well for coding (84.8/100).
- Is hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S good for agentic (tool-using) tasks?
- In our benchmarks, hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S scores 76.0/100 for agentic workflows. It runs at about 71.2 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 hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S for local inference?
- Across 3 community benchmark runs, hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S reaches up to 71.4 tok/s and averages 71.2 tok/s, with the fastest results on Advanced Micro Devices, Inc. [AMD/ATI] Device 7590.
- How much memory does hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S need?
- The leanest observed configuration used about 10.9 GB of memory (quantizations tested: IQ3_S).
- Which tools have been used to run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-IQ3_S?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.