Compare / Qwen3.5 0.8B vs Gemma 3 270M
Qwen3.5 0.8B vs Gemma 3 270M
Updated November 2026
Verdict
Qwen3.5 0.8B and Gemma 3 270M are roughly tied on the Small LM Index (14.2 vs 12.8). On the 6 benchmarks both labs report, Qwen3.5 0.8B wins 4 and Gemma 3 270M wins 2. Both need about 1.2 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick Qwen3.5 0.8B if…
- you need precise instruction following
- you build agents that call tools
- you work with long documents
- you need a permissive license (Apache-2.0)
- you need image input
- you want the more widely used model (more quantized builds and community support)
Pick Gemma 3 270M if…
No clear advantage in the data we have.
Specifications
| Qwen3.5 0.8B | Gemma 3 270M | |
|---|---|---|
| Small LM Index | 14.2 (likely 12–17) | 12.8 (likely 12–14) |
| Lab | Alibaba (Qwen) · China | Google · United States |
| Released | 2026-03-02 | 2025-08-14 |
| Parameters | 900M (dense) | 270M (dense) |
| Memory at 4-bit | ~1.2 GB | ~0.7 GB |
| Context window | 262K tokens | 32K tokens |
| Input | text, image, video | text |
| Reasoning | Hybrid (thinking on/off) | No thinking |
| License | Apache-2.0 | Gemma |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 3.7M | 60.4K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Qwen3.5 0.8B | Gemma 3 270M |
|---|---|---|
| MMLU-Pro Knowledge | 42.3 | 5.5✓ |
| GPQA Diamond Knowledge | 11.1✓ | 22.4✓ |
| Humanity's Last Exam Reasoning | 1.1✓ | 3.6✓ |
| AIME Math | ≈ 3 | 2.3✓ |
| LiveCodeBench Coding | ≈ 5 | 0.3✓ |
| τ²-Bench Agentic | 47.7✓ | 9.1✓ |
| IFBench Instruction following | 21.5✓ | 12.1✓ |
| MMMU-Pro Vision | 25.8✓ | — |
| MMLU Knowledge | 59.5 | — |
| Multilingual MMLU Multilingual | 44.3 | — |
| IFEval Instruction following | 44.0 | — |
| BFCL Agentic | 25.3 | — |
| AA-LCR Long context | 9.0✓ | 0.0✓ |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Qwen3.5 0.8B or Gemma 3 270M?
Qwen3.5 0.8B and Gemma 3 270M are roughly tied on the Small LM Index (14.2 vs 12.8). On the 6 benchmarks both labs report, Qwen3.5 0.8B wins 4 and Gemma 3 270M wins 2.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 1.2 GB of memory at 4-bit quantization.
Which has the longer context window?
Qwen3.5 0.8B has the longer context window: 262K tokens against 32K.
Can I use Qwen3.5 0.8B and Gemma 3 270M commercially?
Qwen3.5 0.8B is released under Apache-2.0 and Gemma 3 270M under Gemma. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.