MODEL COMPARISON
gemma-4-31B-it vs Qwen3.6-35B-A3B
gemma-4-31B-it needs less memory: about 24 GB (text weights only) versus about 29 GB (text weights only) for Qwen3.6-35B-A3B, a difference of 5 GB. gemma-4-31B-it has one runtime in release (Ollama). Qwen3.6-35B-A3B has one runtime in release (Ollama).
SIDE BY SIDE
| Compare | gemma-4-31B-it | Qwen3.6-35B-A3B |
|---|---|---|
| Memory needed | about 24 GB · Up to 32 GB (text weights only) | about 29 GB · Up to 32 GB (text weights only) |
| Recommended quant | Q4_K_M · 18.3 GB | Q4_K_M · 22.3 GB |
| llama.cpp support | Architecture listedChecked 23 Oct 2026 | Architecture listedChecked 23 Oct 2026 |
| Ollama support | ReleasedChecked 23 Oct 2026 | ReleasedChecked 23 Oct 2026 |
| LM Studio support | Upload availableChecked 23 Oct 2026 | Upload availableChecked 23 Oct 2026 |
| MLX / mlx-lm support | Upload availableChecked 23 Oct 2026 | Upload availableChecked 23 Oct 2026 |
| vLLM support | Architecture listedChecked 23 Oct 2026 | Architecture listedChecked 23 Oct 2026 |
| On Hugging Face since | 11 Mar 2026 | 15 Apr 2026 |
| License | Not recorded in this snapshot — see the model card ↗ | Not recorded in this snapshot — see the model card ↗ |
| Publisher | Qwen | |
| Downloads | 8.5M | 3.7M |
| Model page | Open gemma-4-31B-it ↗ | Open Qwen3.6-35B-A3B ↗ |
| Fits these setups |
|
|
Memory needed is the same estimate shown on each model page: the recommended observed file plus 20% headroom and a 1.5 GB runtime allowance. See which setups fit →
These are estimates from observed file sizes, not benchmarks. They don’t account for long contexts or the KV cache, and fitting does not establish runtime compatibility or speed.