Alternatives to Qwen3-VL-Embedding-2B

Qwen3-VL-Embedding-2B alternatives

Qwen3-VL-Embedding-2B's smallest published quantization is 0.72 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
Qwen3.5-0.8B873M0.31 GiB42apache-2.0
Qwen3-VL-2B-Instruct2.1B0.50 GiB46apache-2.0
LFM2.5-VL-1.6B1.6B0.45 GiB23other

Comparable in size

within ±40%, so a like-for-like swap
ModelParamsSmallestQuantsLicence
Qwen3-VL-4B-Instruct4.4B1.01 GiB26apache-2.0
Qwen3.5-2B2.3B0.72 GiB42apache-2.0

More permissively licensed

licences that allow commercial use
ModelParamsSmallestQuantsLicence
Qwen3.6-35B-A3BMoE36.0B8.77 GiB61apache-2.0
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP27.8B10.12 GiB34apache-2.0
Qwen3.5-9B9.7B2.97 GiB34apache-2.0
gemma-4-26B-A4B-itMoE26.5B8.99 GiB46apache-2.0
gemma-4-12B-it12.0B3.92 GiB59apache-2.0
Qwen3.5-4B4.7B1.42 GiB57apache-2.0
Qwythos-9B-Claude-Mythos-5-1M9.4B5.38 GiB16apache-2.0
gemma-4-31B-it31.3B7.95 GiB55apache-2.0