Skip to content
VibekollenBETAVibekollen
ReleaseOllama

v0.40.8: mlx: add Flint model support (#19181)

Article image or reusable cover for Ollama

Preserve source tool JSON alongside decoded API values so Flint can retain numeric types and schema order in prompts.

Existing API marshaling is unchanged. Assemble ModelOpt expert banks during safetensors import, and reject direct Flint NVFP4 creation before conversion. Other models retain their existing import and quantization paths. Add optional learned sinks and device causal masks to shared MLX attention. Existing callers retain the no-sink and host-mask paths; Flint opts into the new behavior.

Read the full story at Ollama →

The text is the source's own description of its publication. The content belongs to Ollama.

More from Ollama