AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit

Model

stars

commits

linked in READMEs

Aug 15, 2026

updated

4-bit

agent

axq

axquant

conversational

development

glimmer

image-text-to-text

mlx

mlx-vlm

multimodal

muse

muse_glimmer

safetensors

README

AX-Muse-Glimmer-30B-MLX-AXQ-4bit

Development AXQuant (AXQ) 4bit MLX pack of meta-models/Muse-Glimmer-30B @ a4e59da52a7bc87ae7251dd5545c0dd437c44b68.

Converted via MLX-VLM muse_glimmer. Language path quantized; vision tower / adapter / projection BF16-preserved.

Not certified for AXQuant checkpoint Tier 1 on df-macstudio-m2 (2026-08-15). MLX-VLM load and generate smoke passed. Dual-suite quality vs BF16 cannot run because evaluate-quality uses the mlx-lm backend, which rejects model_type=muse_glimmer. See the evaluation record.

Claims

Claim	Status
AXQuant architecture-prior / development quant	Yes
Checkpoint Tier 1	Not certified
Dual-suite quality vs BF16	Not measured (mlx-lm backend gap)
MLX-VLM load + generate smoke	Passed on `df-macstudio-m2`
Vision / multimodal quality	Not claimed — vision BF16-protected only
Certified release	No

Source

Official: meta-models/Muse-Glimmer-30B@a4e59da52a7bc87ae7251dd5545c0dd437c44b68 (Apache-2.0)
Adapter: muse-glimmer-v1

Attribution

Base weights © Meta (Apache-2.0). Quantization by AXQuant (development).

Contributors

AutomatosX

3 commits

Similar repos

AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-6bit

Model

shared topics

AutomatosX/AX-DeepSeek-OCR-2-MLX-AXQ-4bit

Model

shared topics

AutomatosX/AX-Qwen3-VL-30B-A3B-Instruct-MLX-AXQ-4bit

Model

shared topics

AutomatosX/AX-DeepSeek-OCR-2-MLX-AXQ-6bit

Model

shared topics

AutomatosX/AX-gemma-4-31b-MLX-AXQ-4bit-MTP

Model

shared topics

AutomatosX/AX-gemma-4-26b-a4b-MLX-AXQ-4bit-MTP

Model

shared topics

AutomatosX/AX-Qwen3-VL-30B-A3B-Instruct-MLX-AXQ-6bit

Model

shared topics

AutomatosX/AX-gemma-4-12b-MLX-AXQ-4bit-MTP

Model

shared topics

Linked in READMEs

defai-digital/axquant

Not another flat 4-bit quantizer. AXQuant mixes precision layer by layer for Apple Silicon—smaller…

README badge

AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit

Model

stars

commits

linked in READMEs

Aug 15, 2026

updated

4-bit

agent

axq

axquant

conversational

development

glimmer

image-text-to-text

mlx

mlx-vlm

multimodal

muse

muse_glimmer

safetensors

README

AX-Muse-Glimmer-30B-MLX-AXQ-4bit

Development AXQuant (AXQ) 4bit MLX pack of meta-models/Muse-Glimmer-30B @ a4e59da52a7bc87ae7251dd5545c0dd437c44b68.

Converted via MLX-VLM muse_glimmer. Language path quantized; vision tower / adapter / projection BF16-preserved.

Not certified for AXQuant checkpoint Tier 1 on df-macstudio-m2 (2026-08-15). MLX-VLM load and generate smoke passed. Dual-suite quality vs BF16 cannot run because evaluate-quality uses the mlx-lm backend, which rejects model_type=muse_glimmer. See the evaluation record.

Claims

Claim	Status
AXQuant architecture-prior / development quant	Yes
Checkpoint Tier 1	Not certified
Dual-suite quality vs BF16	Not measured (mlx-lm backend gap)
MLX-VLM load + generate smoke	Passed on `df-macstudio-m2`
Vision / multimodal quality	Not claimed — vision BF16-protected only
Certified release	No