ggml-org/gpt-oss-20b-GGUF

21B • Updated Oct 30 • 98.5k • 113

Note Can either fit a less vramlet config, or split CPU/GPU usage while keeping a decent speed. Fantastic model all around that stays coherent in many uses, at larger context while being at a size that remains reasonable for most users.

unsloth/Qwen3-4B-Instruct-2507-GGUF

4B • Updated Aug 20 • 65.2k • 105

Note Long context king. Decent at many tasks.

unsloth/Qwen3-4B-Thinking-2507-GGUF

4B • Updated Sep 11 • 15k • 75

Note Long context king++. Performs very well but the wait for the to end can feel long in the tooth.

unsloth/Qwen3-VL-4B-Instruct-GGUF

Image-Text-to-Text • 4B • Updated Oct 31 • 36.3k • 24

Note Best VL model at this size.

unsloth/Qwen3-VL-4B-Thinking-GGUF

Image-Text-to-Text • 4B • Updated Oct 31 • 40.1k • 15

Note Reasoning variant.

unsloth/Qwen3-1.7B-GGUF

Text Generation • 2B • Updated Jun 8 • 61.1k • 56

Note Surprisingly coherent micro model.

ggml-org/Qwen2.5-Coder-1.5B-Q8_0-GGUF

Text Generation • 2B • Updated Oct 28, 2024 • 5k • 11

Note Still the best VRAMlet fill-in-the-middle model for code completion.

Qwen/Qwen3-Embedding-0.6B-GGUF

0.6B • Updated Jul 14 • 22.7k • 470

Note Embed supreme.

quickmt/quickmt-zh-en

Translation • Updated 5 days ago • 43 • 4

Note Not LLM based, but this and the Firefox translation models are about as good as open NMT models get. Very high quality models for fast translation if you do not need the world knowledge / context ingestion / prompt instructions of LLMs.