Model catalog

Qwen3-Coder-30B-A3B-Instruct

Qwen's code model has 30.5B total parameters and 3.3B active per token; weight planning uses the total count.

Check this model on your hardware See what your PC can run

Model overview

Family: Qwen3 Coder
Provider: Qwen
Architecture: Qwen3 MoE
Parameters: 30.5B
Formats: gguf, safetensors
Runtimes: llama.cpp
License: Apache-2.0
Maximum context: 262,144 tokens

Available quantizations

Lower-bit quantizations generally use less memory. The compatibility calculator uses these candidates and its transparent approximate memory assumptions; it does not make a performance guarantee.

Q4_K_M

The conversion repository lists Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf at 18.6 GB; its rounded decimal file size is converted to GiB for planning. This does not include context or runtime memory.

Bits per weight: 4.5
Model size: 17.32 GiB
Source: lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-GGUF GGUF file listing

Compatibility notes

Estimates use the cataloged model-weight size (or a parameter-based estimate), apply weight overhead, and include standard runtime overhead. They do not include context/KV-cache memory. Real requirements vary with runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.

Qwen3-Coder-30B-A3B-Instruct publisher model card; verified value, last verified 2026-09-30. Qwen documents 30.5B total parameters, 3.3B activated parameters, Apache-2.0 licensing, and 262,144-token native context. Weight planning uses total parameters; GGUF details are sourced separately. View source