Llama-4-Scout-17B-16E-6bit
mlx-community/Llama-4-Scout-17B-16E-6bit
Params
—
Weights
—
Mac memory
—
llama4 · updated 2025-04-06
Apple silicon
Apple MLX models
5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
1,022 builds · page 10 of 18 · clear filters
deepseek-vl2-3bit
mlx-community/deepseek-vl2-3bit
Params
27B
Weights
≈ 12.3 GB
Mac memory
16 GB+
deepseek · updated 2024-12-22
deepseek-vl2-small-3bit
mlx-community/deepseek-vl2-small-3bit
Params
16B
Weights
≈ 7.3 GB
Mac memory
16 GB+
deepseek · updated 2024-12-22
gemma-4-26B-A4B-it-qat-5bit
mlx-community/gemma-4-26B-A4B-it-qat-5bit
Params
26B
Weights
≈ 18.5 GB
Mac memory
24 GB+
updated 2026-06-05
Qwen2-VL-7B-Instruct-abliterated-8bit
from Qwen/Qwen2-VL-7B-Instruct
Params
8.3B
Weights
≈ 8.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-24
AutoGLM-Phone-9B-Multilingual-4bit
from zai-org/GLM-4.1V-9B-Base
Params
—
Weights
—
Mac memory
—
mit · updated 2025-12-12
GLM-4.6V-6bit
from zai-org/GLM-4.6V
Params
—
Weights
—
Mac memory
—
mit · updated 2026-02-22
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4.5bit-msq
mlx-community/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4.5bit-msq
Params
40B
Weights
≈ 6.5 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-05-01
gemma-3n-E2B-bf16
from google/gemma-3n-E4B
Params
6.0B
Weights
≈ 10.9 GB
Mac memory
16 GB+
gemma · updated 2025-07-12
Florence-2-large-ft-4bit
mlx-community/Florence-2-large-ft-4bit
Params
823M
Weights
≈ 504 MB
Mac memory
8 GB+
mit · updated 2024-11-21
Qwen2.5-VL-3B-Instruct-abliterated-6bit
from Qwen/Qwen2.5-VL-3B-Instruct
Params
3.8B
Weights
≈ 3.2 GB
Mac memory
8 GB+
updated 2025-02-25
deepseek-vl2-bf16
mlx-community/deepseek-vl2-bf16
Params
27B
Weights
≈ 55.0 GB
Mac memory
64 GB+
deepseek · updated 2024-12-22
Qwen3.5-27B-5bit
mlx-community/Qwen3.5-27B-5bit
Params
27B
Weights
≈ 19.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-02-24
GLM-4.6V-heretic-nvfp4
from coder3101/GLM-4.6V-heretic
Params
108B
Weights
≈ 61.9 GB
Mac memory
96 GB+
updated 2026-03-28
Llama-4-Scout-17B-16E-8bit
mlx-community/Llama-4-Scout-17B-16E-8bit
Params
—
Weights
—
Mac memory
—
llama4 · updated 2025-04-06
deepseek-vl2-tiny-3bit
mlx-community/deepseek-vl2-tiny-3bit
Params
3.4B
Weights
≈ 1.7 GB
Mac memory
8 GB+
deepseek · updated 2024-12-22
gemma-3n-E2B-4bit
from google/gemma-3n-E4B
Params
5.4B
Weights
≈ 4.5 GB
Mac memory
8 GB+
gemma · updated 2026-01-21
Florence-2-base-ft-8bit
mlx-community/Florence-2-base-ft-8bit
Params
271M
Weights
≈ 295 MB
Mac memory
8 GB+
mit · updated 2024-11-21
gemma-3-12b-pt-4bit
from google/gemma-3-12b
Params
—
Weights
—
Mac memory
—
gemma · updated 2025-03-18
pixtral-12b-bf16
mlx-community/pixtral-12b-bf16
Params
13B
Weights
≈ 25.4 GB
Mac memory
32 GB+
updated 2024-10-05
Kestrel-4B-Coder-6bit
from unsloth/Qwen3.5-4B
Params
4.5B
Weights
≈ 4.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-11-07
MiniCPM-V-4.6-8bit
from openbmb/MiniCPM-V-4.6
Params
1.3B
Weights
≈ 2.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-05-13
Unlimited-OCR-6bit
from baidu/Unlimited-OCR
Params
3.3B
Weights
≈ 3.2 GB
Mac memory
8 GB+
mit · updated 2026-07-31
Qwen2-VL-7B-Instruct-abliterated-4bit
from Qwen/Qwen2-VL-7B-Instruct
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-03-24
UI-Venus-1.5-2B-6bit
from inclusionAI/UI-Venus-1.5-2B
Params
2.4B
Weights
≈ 2.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-03-20
deepseek-vl2-small-8bit
mlx-community/deepseek-vl2-small-8bit
Params
16B
Weights
≈ 17.3 GB
Mac memory
24 GB+
deepseek · updated 2024-12-22
gemma-3-27b-it-bf16
from google/gemma-3-27b-pt
Params
—
Weights
—
Mac memory
—
gemma · updated 2025-03-19
gemma-4-26b-a4b-nvfp4
from google/gemma-4-26b-a4b
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-04-03
idefics2-8b-4bit
mlx-community/idefics2-8b-4bit
Params
8.4B
Weights
≈ 4.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-01-29
Qwen3.5-35B-A3B-5bit
mlx-community/Qwen3.5-35B-A3B-5bit
Params
35B
Weights
≈ 24.7 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-02-24
gemma-4-E2B-it-qat-5bit
mlx-community/gemma-4-E2B-it-qat-5bit
Params
5.1B
Weights
≈ 4.1 GB
Mac memory
8 GB+
updated 2026-06-05
idefics2-8b-chatty-4bit
mlx-community/idefics2-8b-chatty-4bit
Params
8.4B
Weights
≈ 4.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-01-29
Ornith-1.0-35B-bf16
from deepreinforce-ai/Ornith-1.0-35B
Params
35B
Weights
≈ 70.2 GB
Mac memory
96 GB+
mit · updated 2026-06-27
Molmo-7B-D-0924-8bit
from Qwen/Qwen2-7B
Params
8.0B
Weights
≈ 9.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-12-27
ERNIE-4.5-VL-28B-A3B-Thinking-4bit
mlx-community/ERNIE-4.5-VL-28B-A3B-Thinking-4bit
Params
29B
Weights
≈ 17.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-01-28
gemma-3n-E4B-bf16
mlx-community/gemma-3n-E4B-bf16
Params
8.4B
Weights
≈ 15.7 GB
Mac memory
24 GB+
gemma · updated 2025-07-12
Qwen3-VL-30B-A3B-Thinking-4bit
mlx-community/Qwen3-VL-30B-A3B-Thinking-4bit
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-10-14
gemma-4-31B-it-qat-nvfp4
mlx-community/gemma-4-31B-it-qat-nvfp4
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+
updated 2026-06-05
DeepSeek-OCR-2-5bit
mlx-community/DeepSeek-OCR-2-5bit
Params
3.4B
Weights
≈ 2.9 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-01-28
GOT-OCR2_0-8bit
from stepfun-ai/GOT-OCR2_0
Params
561M
Weights
≈ 686 MB
Mac memory
8 GB+
apache-2.0 · updated 2026-08-14
Ministral-3-3B-Base-2512-6bit
from mistralai/Ministral-3-3B-Base-2512
Params
3.8B
Weights
≈ 3.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-07-18
SmolVLM-Instruct-8bit
from HuggingFaceTB/SmolVLM-Instruct
Params
2.2B
Weights
≈ 2.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-11-29
Qwen2-VL-72B-Instruct-8bit
mlx-community/Qwen2-VL-72B-Instruct-8bit
Params
73B
Weights
≈ 78.0 GB
Mac memory
96 GB+
tongyi-qianwen · updated 2025-03-24
DeepSeek-OCR-5bit
mlx-community/DeepSeek-OCR-5bit
Params
3.3B
Weights
≈ 2.8 GB
Mac memory
8 GB+
mit · updated 2026-01-28
granite-vision-3.2-2b-nvfp4
from ibm-granite/granite-vision-3.2-2b
Params
3.1B
Weights
≈ 2.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-01
GLM-4.6V-Flash-5bit
mlx-community/GLM-4.6V-Flash-5bit
Params
—
Weights
—
Mac memory
—
mit · updated 2025-12-08
InternVL3-8B-MLX-4bit
from mlx-community/InternVL3-8B-bf16
Params
7.9B
Weights
≈ 4.9 GB
Mac memory
8 GB+
qwen · updated 2026-02-23
gemma-4-31b-6bit
from google/gemma-4-31b
Params
31B
Weights
≈ 26.1 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-04-02
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-bf16
from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Params
33B
Weights
≈ 66.0 GB
Mac memory
96 GB+
nvidia-open-model-agreement · updated 2026-04-29
North-Mini-Code-1.0-5bit
from CohereLabs/North-Mini-Code-1.0
Params
30B
Weights
≈ 22.2 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-06-10
InternVL3-38B-4bit
from OpenGVLab/InternVL3-1B-Instruct
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-04-30
Agents-A1-bf16
from InternScience/Agents-A1
Params
35B
Weights
≈ 70.2 GB
Mac memory
96 GB+
apache-2.0 · updated 2026-07-01
aya-vision-8b-8bit
mlx-community/aya-vision-8b-8bit
Params
8.6B
Weights
≈ 9.6 GB
Mac memory
16 GB+
cc-by-nc-4.0 · updated 2025-03-05
Qwen3.6-35B-A3B-4.4bit-msq
mlx-community/Qwen3.6-35B-A3B-4.4bit-msq
Params
35B
Weights
≈ 5.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-16
GLM-4.6V-Flash-6bit
mlx-community/GLM-4.6V-Flash-6bit
Params
—
Weights
—
Mac memory
—
mit · updated 2025-12-08
Llama-4-Maverick-17B-128E-Instruct-6bit
from meta-llama/Llama-4-Maverick-17B-128E
Params
—
Weights
—
Mac memory
—
llama4 · updated 2025-04-07
gemma-4-31B-it-qat-bf16
mlx-community/gemma-4-31B-it-qat-bf16
Params
31B
Weights
≈ 62.5 GB
Mac memory
96 GB+
updated 2026-06-05
granite-4.0-3b-vision-5bit
from ibm-granite/granite-4.0-3b-vision
Params
4.3B
Weights
≈ 3.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-01
NuExtract3-bf16
from numind/NuExtract3
Params
4.5B
Weights
≈ 9.1 GB
Mac memory
16 GB+
updated 2026-05-20
GLM-4.1V-9B-Thinking-5bit
from zai-org/GLM-4-9B-0414
Params
—
Weights
—
Mac memory
—
mit · updated 2025-11-10