Q4_K_M
The conversion repository lists Qwen3.6-35B-A3B-Q4_K_M.gguf at 20.4 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
- 19.01 GiB
Model catalog
Qwen3.6 35B-A3B
Qwen's 35B multimodal MoE has 3B active parameters per token. Weight planning uses 35B total parameters; the separate vision projector is excluded.
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.
Qwen3.6 35B-A3B publisher model card; verified value, last verified 2026-09-29. The publisher's 35B-A3B designation identifies total and active parameter scales; weight planning uses 35B total parameters. The publisher card documents Apache-2.0 licensing and 262,144-token context. GGUF conversion and separate vision-projector provenance are recorded independently. View source
Multimodal memory scope: This estimate excludes the separate vision/projector file and its runtime memory. ggml-org Qwen3.6 35B-A3B GGUF repository