Q4_K_M
The conversion repository lists Qwen3VL-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
Model catalog
Qwen3-VL-30B-A3B-Instruct
Qwen's multimodal MoE has 31B total and 3B active parameters. Weight planning uses total parameters; the vision projector and multimodal runtime memory are not estimated separately.
Model overview
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.
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-VL-30B-A3B-Instruct publisher model card; verified value, last verified 2026-10-01. Qwen documents 30B-A3B as a 31B total-parameter multimodal MoE with 3B active parameters, Apache-2.0 licensing, and 256K context. Weight planning uses total parameters. View source
Multimodal memory scope: This estimate excludes the separate vision/projector file and its runtime memory. Qwen Qwen3-VL-30B-A3B-Instruct GGUF repository