Alternatives to Yi-Coder-1.5B-Chat

Yi-Coder-1.5B-Chat alternatives

Yi-Coder-1.5B-Chat's smallest published quantization is 0.46 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
ModelParamsSmallestQuantsLicence
ced-base86M0.12 GiB3apache-2.0
embeddinggemma-300m303M0.26 GiB10—
Qwen3-0.6B752M0.20 GiB44—
Qwen2.5-0.5B-Instruct494M0.31 GiB32apache-2.0

Comparable in size

within ±40%, so a like-for-like swap
ModelParamsSmallestQuantsLicence
Llama-3.2-1B-Instruct1.2B0.39 GiB39—
gemma-3-1b-it1000M0.52 GiB28gemma
Qwen3-1.7B2.0B0.50 GiB48—
Wan2.1-T2V-1.3B1.4B0.61 GiB31—
LFM2.5-1.2B-Instruct1.2B0.45 GiB23other
Qwen2.5-1.5B-Instruct1.5B0.56 GiB32apache-2.0
MiniCPM5-1B-Claude-Opus-Fable5-Thinking1.1B0.43 GiB15apache-2.0

More permissively licensed

licences that allow commercial use
ModelParamsSmallestQuantsLicence
Qwen3-Coder-30B-A3B-InstructMoE30.5B7.46 GiB46apache-2.0
Qwen3.6-27B27.8B8.74 GiB40apache-2.0
Qwen3.8-27B27.8B8.39 GiB22apache-2.0
DeepSeek-V4-FlashMoE291B76.87 GiB12mit
gemma-4-12B-it-qat-q4_0-unquantized12.0B6.50 GiB2apache-2.0
gemma-4-E4B-it8.0B3.30 GiB36apache-2.0
Qwen3-30B-A3B-Thinking-2507MoE30.5B7.05 GiB51apache-2.0
Qwen3-8B8.2B2.12 GiB51apache-2.0