Q4_0
The conversion repository lists Qwen3.5-0.8B-Q4_0.gguf at 563 MB; 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
- 0.52 GiB
Model catalog
Qwen3.5 0.8B
Qwen's compact text-and-image model; listed GGUF file sizes are used for weight planning, while vision-processing memory is not estimated.
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.
Q8_0
The conversion repository lists Qwen3.5-0.8B-Q8_0.gguf at 834 MB; its rounded decimal file size is converted to GiB for planning. This does not include context or runtime memory.
- Bits per weight
- 8
- Model size
- 0.78 GiB
Compatibility notes
Weight estimates are approximate and include a runtime overhead. Real requirements vary with context length, runtime, drivers, and other system use. A model page cannot determine compatibility without your hardware profile; use the calculator for that assessment.
Qwen3.5 0.8B publisher model card; verified value, last verified 2026-09-27. The publisher identifies the 0.8B multimodal model, Apache-2.0 license, and native 262,144-token context. GGUF files and listed sizes are attributed separately to the ggml-org conversion; vision-processing memory is not estimated. View source