Alternatives to granite-4.0-1b
granite-4.0-1b alternatives
granite-4.0-1b's smallest published quantization is 0.44 GiB. The models below do the same job with a different trade — less memory, comparable size, or a more permissive licence.
From the file· sizes from summed file bytes
Meaningfully smaller
under 70% of its smallest quantization
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| ced-base | 86M | 0.12 GiB | 3 | apache-2.0 |
| embeddinggemma-300m | 303M | 0.26 GiB | 10 | — |
| Qwen3-0.6B | 752M | 0.20 GiB | 44 | — |
| Qwen2.5-0.5B-Instruct | 494M | 0.31 GiB | 32 | apache-2.0 |
Comparable in size
within ±40%, so a like-for-like swap
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| Llama-3.2-1B-Instruct | 1.2B | 0.39 GiB | 39 | — |
| gemma-3-1b-it | 1000M | 0.52 GiB | 28 | gemma |
| Qwen3-1.7B | 2.0B | 0.50 GiB | 48 | — |
| Wan2.1-T2V-1.3B | 1.4B | 0.61 GiB | 31 | — |
| LFM2.5-1.2B-Instruct | 1.2B | 0.45 GiB | 23 | other |
| Qwen2.5-1.5B-Instruct | 1.5B | 0.56 GiB | 32 | apache-2.0 |
| MiniCPM5-1B-Claude-Opus-Fable5-Thinking | 1.1B | 0.43 GiB | 15 | apache-2.0 |
More permissively licensed
licences that allow commercial use
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| Qwen3-Coder-30B-A3B-InstructMoE | 30.5B | 7.46 GiB | 46 | apache-2.0 |
| Qwen3.6-27B | 27.8B | 8.74 GiB | 40 | apache-2.0 |
| Qwen3.8-27B | 27.8B | 8.39 GiB | 22 | apache-2.0 |
| DeepSeek-V4-FlashMoE | 291B | 76.87 GiB | 12 | mit |
| gemma-4-12B-it-qat-q4_0-unquantized | 12.0B | 6.50 GiB | 2 | apache-2.0 |
| gemma-4-E4B-it | 8.0B | 3.30 GiB | 36 | apache-2.0 |
| Qwen3-30B-A3B-Thinking-2507MoE | 30.5B | 7.05 GiB | 51 | apache-2.0 |
| Qwen3-8B | 8.2B | 2.12 GiB | 51 | apache-2.0 |