All news
2026-08-15CATALOG

Added to the catalog: Qwen3 4B Instruct 2507

Catalog idqwen3-4b-instruct
Sourceunsloth/Qwen3-4B-Instruct-2507-GGUF
Quant · sizeQ4_K_M · 2.5 GB
Tool callingyes — native llama.cpp parser

Qwen3 4B Instruct (the 2507 refresh, non-thinking) is a first-class catalog entry. At 2.5 GB it sits in the sweet spot for local work: comfortable on an 8 GB machine, quick to download, and strong for its size on instruction following and tool use.

What "in the catalog" means here — this is the checklist every adaptation post reports:

omg model pull qwen3-4b-instruct
omg run qwen3-4b-instruct

Notes: the default context is the runtime's 8192; raise it per-start with --context-length if you have the memory. If you want a different quant, pull it directly with an hf: reference — unsupported, usually fine.


Full catalog → · Model card on Hugging Face →