SongGeneration-v2-medium-4bit
from tencent/SongGeneration
Params
2.8B
Weights
≈ 1.6 GB
Mac memory
8 GB+
other · updated 2026-05-31
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 51 of 98
3b-ko-ft-research_release-bf16
from canopylabs/orpheus-3b-0.1-pretrained
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-04-09
AIDC-AI_Marco-o1_MLX-8bit
from ATH-MaaS/Marco-o1
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-11-27
DeepSeek-Prover-V2-7B-8bit
from deepseek-ai/DeepSeek-Prover-V2-7B
Params
6.9B
Weights
≈ 7.3 GB
Mac memory
16 GB+
updated 2025-06-02
DeepSeek-R1-Distill-Llama-8B-3bit
from deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Params
8.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+
updated 2025-02-26
DeepSeek-R1-Distill-Llama-8B-8bit-mlx
from deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
updated 2025-02-26
Falcon-H1-Tiny-Multilingual-100M-Instruct-4bit
from tiiuae/Falcon-H1-Tiny-Multilingual-100M-Instruct
Params
108M
Weights
≈ 61 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
GLM-Z1-9B-0414-6bit
from zai-org/GLM-Z1-9B-0414
Params
9.4B
Weights
≈ 7.6 GB
Mac memory
16 GB+
mit · updated 2025-04-21
GLM-Z1-9B-0414-8bit
from zai-org/GLM-Z1-9B-0414
Params
9.4B
Weights
≈ 10.0 GB
Mac memory
16 GB+
mit · updated 2025-04-21
Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-8bit
from Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1
Params
494M
Weights
≈ 525 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-11-17
Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-8-bit
from Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-12-08
Josiefied-Qwen3.5-0.8B-gabliterated-v1-mxfp4
from Goekdeniz-Guelmez/Josiefied-Qwen3.5-0.8B-gabliterated-v1
Params
752M
Weights
≈ 424 MB
Mac memory
8 GB+
updated 2026-03-13
Ministral-3-8B-Base-2512-8bit
from mistralai/Ministral-3-8B-Base-2512
Params
8.9B
Weights
≈ 10.4 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-07-18
Ministral-3-8B-Base-2512-bf16
from mistralai/Ministral-3-8B-Base-2512
Params
8.9B
Weights
≈ 17.8 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-07-18
Mixtral-SlimOrca-8x7B-3bit
from Open-Orca/Mixtral-SlimOrca-8x7B
Params
47B
Weights
≈ 20.4 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-02-19
OLMo-2-1124-7B-Instruct-8bit
from allenai/OLMo-2-1124-7B-Instruct
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-11-27
Qwen2.5-32B-bf16
mlx-community/Qwen2.5-32B-bf16
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2024-09-18
Qwen2.5-Math-72B-Instruct-8bit
from Qwen/Qwen2.5-Math-72B
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+
qwen · updated 2024-09-19
Qwen3-0.6B-4bit-DWQ-05092025
from Qwen/Qwen3-0.6B
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-05-10
Qwen3-16B-A3B-bf16
from kalomaze/Qwen3-16B-A3B
Params
16B
Weights
≈ 32.1 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-05-03
Step-Audio-EditX-8bit
from stepfun-ai/Step-Audio-EditX
Params
3.5B
Weights
≈ 3.8 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-10-07
VisualQuality-R1-7B-8bit
from Qwen/Qwen2.5-VL-7B-Instruct
Params
—
Weights
—
Mac memory
—
mit · updated 2025-08-06
gemma-3-1b-it-6bit
from google/gemma-3-1b-it
Params
1.3B
Weights
≈ 1.1 GB
Mac memory
8 GB+
gemma · updated 2025-03-12
gemma-4-12B-it-qat-assistant-6bit
from google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
Params
423M
Weights
≈ 344 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
gemma-4-31B-it-qat-assistant-mxfp4
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-3b-code-base-4bit
mlx-community/granite-3b-code-base-4bit
Params
3.5B
Weights
≈ 2.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-05-06
sapiens2-matting-1b-bf16
from facebook/sapiens2-matting-1b
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+
sapiens2-license · updated 2026-09-13
tasksource-ModernBERT-base-embed-4bit
from answerdotai/ModernBERT-base
Params
149M
Weights
≈ 84 MB
Mac memory
8 GB+
updated 2025-04-02
whisper-base-khmer-mlx-fp16
from openai-whisper-base
Params
72M
Weights
≈ 144 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-25
whisper-base.en-mlx-4bit
mlx-community/whisper-base.en-mlx-4bit
Params
—
Weights
—
Mac memory
—
updated 2024-03-09
whisper-tiny.en-mlx-4bit
mlx-community/whisper-tiny.en-mlx-4bit
Params
—
Weights
—
Mac memory
—
updated 2024-03-09
Ling-2.6-flash-mlx-4bit-gs32
from inclusionAI/Ling-2.6-flash
Params
104B
Weights
≈ 58.6 GB
Mac memory
96 GB+
mit · updated 2026-04-29
MiniMax-M2-3bit
from MiniMaxAI/MiniMax-M2
Params
229B
Weights
≈ 100 GB
Mac memory
128 GB+
mit · updated 2025-10-28
NemotronLabs-VoiceChat-11B-mlx-4bit
from nvidia/NVIDIA-NemotronLabs-VoiceChat-11B
Params
3.1B
Weights
≈ 5.1 GB
Mac memory
8 GB+
openmdw-1.1 · updated 2026-08-05
defog-sqlcoder-7b-2
mlx-community/defog-sqlcoder-7b-2
Params
—
Weights
—
Mac memory
—
cc-by-sa-4.0 · updated 2024-02-07
meditron-7b
from epfl-llm/meditron-7b
Params
6.7B
Weights
≈ 3.8 GB
Mac memory
8 GB+
llama2 · updated 2025-01-25
AnimeGen-I2V-A14B-Lightning-bf16
from Wan-AI/Wan2.2-I2V-A14B
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2026-07-14
DeepSeek-V2.5-1210-3bit
from deepseek-ai/DeepSeek-V2.5-1210
Params
236B
Weights
≈ 103 GB
Mac memory
128 GB+
deepseek · updated 2024-12-11
DeepSeek-V2.5-MLX-AQ4_1_64
from deepseek-ai/DeepSeek-V2.5
Params
236B
Weights
≈ 133 GB
Mac memory
192 GB+
deepseek · updated 2024-09-07
GLM-4.5-Air-2bit-DWQ
from zai-org/GLM-4.5-Air
Params
107B
Weights
≈ 33.4 GB
Mac memory
48 GB+
mit · updated 2025-08-03
IQuest-Coder-V1-40B-Instruct-4bit
from IQuestLab/IQuest-Coder-V1-40B-Instruct
Params
40B
Weights
≈ 22.4 GB
Mac memory
32 GB+
iquestcoder · updated 2026-01-01
Qwen1.5-72B-Chat-4bit
mlx-community/Qwen1.5-72B-Chat-4bit
Params
72B
Weights
≈ 42.5 GB
Mac memory
64 GB+
tongyi-qianwen · updated 2024-03-08
SmolLM-135M-Instruct-8bit
mlx-community/SmolLM-135M-Instruct-8bit
Params
135M
Weights
≈ 143 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-07-16
dolphin-2.9.2-qwen2-72b-8bit
from Qwen/Qwen2-72B
Params
20B
Weights
≈ 23.9 GB
Mac memory
32 GB+
tongyi-qianwen · updated 2024-06-07
Gemma-2-9B-It-SPPO-Iter3-4bit
mlx-community/Gemma-2-9B-It-SPPO-Iter3-4bit
Params
9.2B
Weights
≈ 5.2 GB
Mac memory
8 GB+
gemma · updated 2024-07-16
LFM2.5-1.2B-JP-4bit
from LiquidAI/LFM2.5-1.2B-JP
Params
1.2B
Weights
≈ 659 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-01-06
LLaDA-8B-Instruct-mlx-4bit
from GSAI-ML/LLaDA-8B-Instruct
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
mit · updated 2025-03-12
Qwen1.5-14B-Chat-4bit
mlx-community/Qwen1.5-14B-Chat-4bit
Params
14B
Weights
≈ 9.1 GB
Mac memory
16 GB+
tongyi-qianwen · updated 2024-03-08
Qwen3-32B-4bit-DWQ
from mlx-community/Qwen3-32B-8bit
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-05-17
Tiger-Gemma-9B-v3-Q4-mlx
from TheDrummer/Tiger-Gemma-9B-v3
Params
9.2B
Weights
≈ 5.2 GB
Mac memory
8 GB+
updated 2025-01-06
aya-vision-8b-4bit
mlx-community/aya-vision-8b-4bit
Params
8.6B
Weights
≈ 5.4 GB
Mac memory
16 GB+
cc-by-nc-4.0 · updated 2025-03-05
gemma-4-12B-it-assistant-nvfp4
from google/gemma-4-12B-it-assistant
Params
423M
Weights
≈ 238 MB
Mac memory
8 GB+
apache-2.0 · updated 2026-06-03
sarvam-1-4bit
from sarvamai/sarvam-1
Params
2.5B
Weights
≈ 1.4 GB
Mac memory
8 GB+
updated 2024-10-24
AceReason-Nemotron-1.1-7B-4bit
from nvidia/AceReason-Nemotron-1.1-7B
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
nvidia-open-model-license · updated 2025-06-17
Falcon3-10B-Instruct-abliterated-4bit
from huihui-ai/Falcon3-10B-Instruct-abliterated
Params
10B
Weights
≈ 5.8 GB
Mac memory
16 GB+
falcon-llm-license · updated 2025-02-19
Mistral-NeMo-Minitron-8B-Instruct
from nvidia/Mistral-NeMo-Minitron-8B-Base
Params
8.4B
Weights
≈ 16.8 GB
Mac memory
24 GB+
nvidia-community-model-license · updated 2024-10-04
MolmoPoint-8B-6bit
from Qwen/Qwen3-8B
Params
8.7B
Weights
≈ 9.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-21
QwQ-32B-3bit
from Qwen/QwQ-32B
Params
33B
Weights
≈ 14.3 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-05
Solar-Open-100B-6bit
from upstage/Solar-Open-100B
Params
103B
Weights
≈ 83.4 GB
Mac memory
96 GB+
solar-apache-2.0 · updated 2026-01-06
SongGeneration-v2-medium-bf16
from tencent/SongGeneration
Params
2.8B
Weights
≈ 5.6 GB
Mac memory
16 GB+
other · updated 2026-05-31