4-5B Parameter LLMs

gemma-4-E4B-it

Qwen3.5-4B

Qwen3-4B

LightOnOCR-3-4B

gemma-3-4b-it

Qwen3-VL-4B-Instruct

Qwen3-4B-Instruct-2507

gemma-4-E4B

Phi-3-mini-4k-instruct

Lythri-Tada-4B

Qwen3-Embedding-4B

Nanbeige4.1-3B

Nemotron-3.5-Content-Safety

Rhea-4B-Coding-max

Agents-A1-4B

Gemma-3-Gaia-PT-BR-4b-it

Huihui-Qwen3.5-4B-abliterated

Tev1-4B-experimental

StartLux-Decision-v1.1-4B-Instant

Huihui-Qwen3-VL-4B-Instruct-abliterated

K2-Horizon-3.7B

Qwen3-VL-4B-Instruct

Qwen3-VL-4B-Thinking

fable-traces

Qwen3-4B-Thinking-2507

gemma-4-E2B-it

Qwen3.5-4B-Uncensored-Aggressive

Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark

StartLux-Decision-v1-4B

Nemotron-3-Content-Safety

Pythagoras-Prover-4B

Qwen3-VL-4B-Instruct

medgemma-1.5-4b-it

Qwen3-VL-4B-Instruct-Uncensored

gemma-4-E2B-it-uncensored

Qwen3-VL-4B-Instruct-Uncensored-FP8

VISTA-4B

Orca-2-4B-Coding-max

Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING

XORTRON.CriminalComputing.2026.4B.Instruct.NEXT

APUS-Reflex-4B

Apodex-1.0-4B-SFT