aanaphi2-v0.1-4bit
mlx-community/aanaphi2-v0.1-4bit
Params
546M
Weights
≈ 616 MB
Mac memory
8 GB+
updated 2024-04-20
Apple silicon
Apple MLX models
5,842 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 2h ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
5,842 builds · page 52 of 98
belle-whisper-large-v3-zh-8bit
mlx-community/belle-whisper-large-v3-zh-8bit
Params
1.5B
Weights
≈ 1.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-05-30
distil-whisper-medium.en
mlx-community/distil-whisper-medium.en
Params
—
Weights
—
Mac memory
—
updated 2024-08-14
dolphin-2.8-mistral-7b-v02-4bit
from mistral-community/Mistral-7B-v0.2
Params
7.2B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-04-06
gemma-3-4b-it-abliterated-bf16-text
from mlabonne/gemma-3-4b-it-abliterated
Params
4.6B
Weights
≈ 9.1 GB
Mac memory
16 GB+
gemma · updated 2025-03-22
gemma-4-31B-it-qat-assistant-5bit
from google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
Params
470M
Weights
≈ 323 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
gemma-4-31B-it-qat-assistant-nvfp4
from google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
Params
470M
Weights
≈ 264 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
granite-4.0-3b-vision-mxfp4
from ibm-granite/granite-4.0-3b-vision
Params
4.3B
Weights
≈ 3.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-01
Llama-3-70B-Instruct-Gradient-1048k-8bit
mlx-community/Llama-3-70B-Instruct-Gradient-1048k-8bit
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+
llama3 · updated 2024-05-05
Mistral-7B-Instruct-v0.2-4bit-mlx
mlx-community/Mistral-7B-Instruct-v0.2-4bit-mlx
Params
—
Weights
—
Mac memory
—
updated 2024-01-03
Llama-3-8B-Instruct-262k-8bit
mlx-community/Llama-3-8B-Instruct-262k-8bit
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2024-05-05
AREX-Turbo-6bit
from BAAI/AREX-Turbo
Params
4.5B
Weights
≈ 4.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-07-28
HiDream-O1-Image-Dev-mlx-q8
from HiDream-ai/HiDream-O1-Image-Dev
Params
8.8B
Weights
≈ 10.0 GB
Mac memory
16 GB+
mit · updated 2026-05-11
audiogen-medium-mlx
from facebook/audiogen-medium
Params
1.9B
Weights
≈ 3.9 GB
Mac memory
8 GB+
cc-by-nc-4.0 · updated 2026-05-29
gemma-2-27b-8bit
mlx-community/gemma-2-27b-8bit
Params
27B
Weights
≈ 28.9 GB
Mac memory
48 GB+
gemma · updated 2024-06-27
numind-NuExtract-1.5-MLX-4bit
from numind/NuExtract-1.5
Params
3.8B
Weights
≈ 2.1 GB
Mac memory
8 GB+
mit · updated 2024-11-27
numind-NuExtract-1.5-MLX-8bit
from numind/NuExtract-1.5
Params
3.8B
Weights
≈ 4.1 GB
Mac memory
8 GB+
mit · updated 2024-11-27
plamo-2-1b-bf16
from pfnet/plamo-2-1b
Params
1.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-03-15
Athene-V2-Chat-4bit
from Nexusflow/Athene-V2-Chat
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+
other · updated 2024-12-09
Dracarys2-72B-Instruct-8bit
from abacusai/Dracarys2-72B-Instruct
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+
tongyi-qianwen · updated 2024-10-06
Jan-v1-4B-4bit
from janhq/Jan-v1-4B
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-08-12
Kimi-K2-Thinking-3bit
from moonshotai/Kimi-K2-Thinking
Params
1.0T
Weights
≈ 449 GB
Mac memory
512 GB+
modified-mit · updated 2025-11-25
Mistral-NeMo-Minitron-8B-Instruct-8bit
from nvidia/Mistral-NeMo-Minitron-8B-Base
Params
8.4B
Weights
≈ 8.9 GB
Mac memory
16 GB+
nvidia-community-model-license · updated 2024-10-04
Mistral-Small-Instruct-2409-4bit
mlx-community/Mistral-Small-Instruct-2409-4bit
Params
22B
Weights
≈ 12.5 GB
Mac memory
16 GB+
mrl · updated 2024-09-17
Qwen3-32B-bf16
from Qwen/Qwen3-32B
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-04-28
SmolLM-135M-fp16
mlx-community/SmolLM-135M-fp16
Params
135M
Weights
≈ 269 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-07-16
SongGeneration-v2-medium-8bit
from tencent/SongGeneration
Params
2.8B
Weights
≈ 3.0 GB
Mac memory
8 GB+
other · updated 2026-05-31
Tmax-9B-MLX-8bit
from allenai/tmax-9b
Params
9.0B
Weights
≈ 9.5 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-06-25
Wayfarer-Large-70B-Llama-3.3-3bit
from LatitudeGames/Wayfarer-Large-70B-Llama-3.3
Params
71B
Weights
≈ 30.9 GB
Mac memory
48 GB+
llama3.3 · updated 2025-02-20
granite-4.0-1b-speech-5bit
from ibm-granite/granite-4.0-1b-base
Params
2.3B
Weights
≈ 2.2 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-03-11
llava-v1.6-34b-4bit
mlx-community/llava-v1.6-34b-4bit
Params
35B
Weights
≈ 19.6 GB
Mac memory
24 GB+
updated 2024-10-06
AceReason-Nemotron-14B-8bit
from nvidia/AceReason-Nemotron-14B
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+
nvidia-open-model-license · updated 2025-05-24
AutoGLM-Phone-9B-Multilingual-6bit
from zai-org/GLM-4.1V-9B-Base
Params
—
Weights
—
Mac memory
—
mit · updated 2025-12-15
CodeLlama-7b-hf-4bit-mlx
from codellama/CodeLlama-7b-hf
Params
6.7B
Weights
≈ 3.8 GB
Mac memory
8 GB+
llama2 · updated 2025-04-27
EVA-Qwen2.5-72B-v0.0
from EVA-UNIT-01/EVA-Qwen2.5-72B-v0.0
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+
qwen · updated 2024-10-31
Falcon3-1B-Instruct-3bit
from tiiuae/Falcon3-1B-Instruct
Params
1.7B
Weights
≈ 730 MB
Mac memory
8 GB+
falcon-llm-license · updated 2024-12-17
Laguna-M.1-4bit
from poolside/Laguna-M.1
Params
226B
Weights
≈ 127 GB
Mac memory
192 GB+
apache-2.0 · updated 2026-06-18
Llama-160M-Chat-v1-4bit-mlx
from JackFram/llama-160m
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2024-01-10
LongCat-Flash-Lite-Sparse-8bit
from meituan-longcat/LongCat-Flash-Lite-Sparse
Params
69B
Weights
≈ 72.9 GB
Mac memory
96 GB+
mit · updated 2026-08-31
MIST-1-70B-8bit-MLX
mlx-community/MIST-1-70B-8bit-MLX
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+
updated 2026-05-31
Mellum2-12B-A2.5B-Instruct-bf16
from JetBrains/Mellum2-12B-A2.5B-Instruct
Params
12B
Weights
≈ 24.3 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-08-11
Metric-Video-Depth-Anything-Base-MLX
mlx-community/Metric-Video-Depth-Anything-Base-MLX
Params
115M
Weights
≈ 458 MB
Mac memory
8 GB+
cc-by-nc-4.0 · updated 2026-09-01
Qwen-3-VL-Ricoh-8B-20260227-MLX-4bit
from ricoh-ai/Qwen-3-VL-Ricoh-8B-20260227
Params
8.8B
Weights
≈ 5.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-30
Qwen2-VL-7B-Instruct-abliterated
from Qwen/Qwen2-VL-7B-Instruct
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-24
dots.mocr-mxfp8
from dots-studio/dots.mocr
Params
3.0B
Weights
≈ 4.4 GB
Mac memory
8 GB+
mit · updated 2026-04-03
gemma-3-1b-pt-8bit
from google/gemma-3-1b-pt
Params
1.3B
Weights
≈ 1.4 GB
Mac memory
8 GB+
gemma · updated 2025-03-12
granite-speech-4.1-2b-nar-mlx-5bit
from ibm-granite/granite-speech-4.1-2b-nar
Params
2.3B
Weights
≈ 2.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-05-28
llm-jp-3.1-13b-instruct4-4bit
from llm-jp/llm-jp-3.1-13b-instruct4
Params
14B
Weights
≈ 7.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-06-16
unimate-uniml3d-f60-v3-bf16
from Linzhan/UniMate
Params
184M
Weights
≈ 367 MB
Mac memory
8 GB+
cc-by-nc-4.0 · updated 2026-10-14
jinaai-ReaderLM-v2
from jinaai/ReaderLM-v2
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+
mit · updated 2025-01-17
Forgotten-Safeword-24B-4bit
from ReadyArt/Forgotten-Safeword-24B
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+
mrl · updated 2025-02-22
DeepSeek-R1-0528-5bit
from deepseek-ai/DeepSeek-R1-0528
Params
671B
Weights
≈ 461 GB
Mac memory
> 512 GB
mit · updated 2025-07-01
GLM-4-32B-0414-4bit-DWQ
from THUDM/GLM-4-32B-0414
Params
33B
Weights
≈ 18.3 GB
Mac memory
24 GB+
mit · updated 2025-05-22
LLaDA2.0-mini-4bit
from inclusionAI/LLaDA2.0-mini
Params
16B
Weights
≈ 9.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-11-25
ERNIE-4.5-21B-A3B-PT-8bit
from baidu/ERNIE-4.5-21B-A3B-PT
Params
22B
Weights
≈ 23.2 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-07-04
gemma-3-27b-pt-4bit
mlx-community/gemma-3-27b-pt-4bit
Params
—
Weights
—
Mac memory
—
gemma · updated 2025-03-18
gemma-3n-E4B-it-8bit
from google/gemma-3n-E4B
Params
—
Weights
—
Mac memory
—
gemma · updated 2025-07-12
AI21-Jamba-Reasoning-3B-6bit
from ai21labs/AI21-Jamba-Reasoning-3B
Params
3.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-14
DeepSeek-v3-0324-8bit
from deepseek-ai/DeepSeek-v3-0324
Params
671B
Weights
≈ 713 GB
Mac memory
> 512 GB
mit · updated 2025-04-02
Falcon-H1-Tiny-Coder-90M-8bit
from tiiuae/Falcon-H1-Tiny-Coder-90M
Params
91M
Weights
≈ 97 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28