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
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
2,922 builds · page 26 of 49 · clear filters
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
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
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
defog-sqlcoder-7b-2
mlx-community/defog-sqlcoder-7b-2
Params
—
Weights
—
Mac memory
—
cc-by-sa-4.0 · updated 2024-02-07
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
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
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
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
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
aanaphi2-v0.1-4bit
mlx-community/aanaphi2-v0.1-4bit
Params
546M
Weights
≈ 616 MB
Mac memory
8 GB+
updated 2024-04-20
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
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
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
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
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
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
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
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
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
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