Jeffrey Morgan 03bf241c33 x/imagegen: add FP4 quantization support for image generation models (#13773) ...

Add --quantize fp4 support to ollama create for image generation models
(flux2, z-image-turbo), using MLX's affine 4-bit quantization.

Changes:
- Add fp4 to validation in CreateImageGenModel
- Add FP4 case to quantizeTensor (group_size=32, bits=4, affine mode)
- Add GetQuantization() to WeightSource interface for dynamic params
- Update LoadLinearLayer to use quantization params from model metadata

2026-01-19 00:54:54 -08:00

..

agent

x/cmd: enable web search and web fetch with flag (#13690)

2026-01-12 13:59:40 -08:00

cmd

cmd: enable multi-line input and shift enter (#13694)

2026-01-14 17:52:46 -08:00

create

x/imagegen: add FP4 quantization support for image generation models (#13773)

2026-01-19 00:54:54 -08:00

imagegen

x/imagegen: add FP4 quantization support for image generation models (#13773)

2026-01-19 00:54:54 -08:00

kvcache

Add experimental MLX backend and engine with imagegen support (#13648)

2026-01-08 16:18:59 -08:00

ml

MLX - dynamic loading of mlx-c (#13735)

2026-01-16 16:34:22 -08:00

model

Add experimental MLX backend and engine with imagegen support (#13648)

2026-01-08 16:18:59 -08:00

server

Fix create and show commands for experimental models (#13741)

2026-01-16 14:31:55 -08:00

tools

x/cmd: enable web search and web fetch with flag (#13690)

2026-01-12 13:59:40 -08:00