Q4_K_M
The conversion repository lists Qwen3.6-27B-Q4_K_M.gguf at 19.1 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
- 17.79 GiB
Model catalog
Qwen3.6 27B
Qwen's 27B multimodal model. Listed GGUF sizing covers the main model weights and excludes the separate vision projector.
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 27B publisher model card; verified value, last verified 2026-09-29. The publisher identifies Qwen3.6-27B as a 27B multimodal model under Apache-2.0 with 262,144-token context. GGUF file sizing is separately attributed to ggml-org; the separate vision projector is outside this weight estimate. View source
Multimodal memory scope: This estimate excludes the separate vision/projector file and its runtime memory. ggml-org Qwen3.6 27B GGUF repository