MiniMax-M2-6bit
from MiniMaxAI/MiniMax-M2
Params
229B
Weights
≈ 186 GB
Mac memory
256 GB+
mit · updated 2025-10-28
Apple silicon
Apple MLX models
5,842 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 14m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 39 of 49 · clear filters
ERNIE-4.5-0.3B-PT-bf16
from baidu/ERNIE-4.5-0.3B-PT
Params
361M
Weights
≈ 721 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-07-02
Falcon3-1B-Instruct-bf16
from tiiuae/Falcon3-1B-Instruct
Params
1.7B
Weights
≈ 3.3 GB
Mac memory
8 GB+
falcon-llm-license · updated 2024-12-17
Nanbeige4.1-3B-heretic-bfloat16
from heretic-org/Nanbeige4.1-3B-heretic
Params
3.9B
Weights
≈ 7.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-02-17
Nex-N2-mini-6bit
from nex-agi/Nex-N2-mini
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-06-08
Qwen3-235B-A22B-Thinking-2507-3bit
from Qwen/Qwen3-235B-A22B-Thinking-2507
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+
apache-2.0 · updated 2025-07-25
Trinity-Large-Preview-8bit
from arcee-ai/Trinity-Large-Preview
Params
399B
Weights
≈ 424 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-02-10
deepcogito-cogito-v1-preview-llama-70B-fp16
from deepcogito/cogito-v1-preview-llama-70B
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+
llama3.1 · updated 2025-04-09
orpheus-3b-0.1-pretrained-4bit
from canopylabs/orpheus-3b-0.1-pretrained
Params
3.3B
Weights
≈ 1.9 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-04-02
Agatha-111B-v1-4bit
from TheDrummer/Agatha-111B-v1
Params
111B
Weights
≈ 62.5 GB
Mac memory
96 GB+
updated 2025-06-12
Anubis-70B-v1.1-6bit
from TheDrummer/Anubis-70B-v1.1
Params
71B
Weights
≈ 57.3 GB
Mac memory
96 GB+
updated 2025-06-28
CodeLlama-13b-hf-6bit-mlx
from codellama/CodeLlama-13b-hf
Params
13B
Weights
≈ 10.6 GB
Mac memory
16 GB+
llama2 · updated 2025-04-27
CodeLlama-7b-Instruct-hf-6bit-mlx
from codellama/CodeLlama-7b-Instruct-hf
Params
6.7B
Weights
≈ 5.5 GB
Mac memory
16 GB+
llama2 · updated 2025-04-27
EXAONE-Deep-32B-bf16
from LGAI-EXAONE/EXAONE-Deep-32B
Params
32B
Weights
≈ 64.0 GB
Mac memory
96 GB+
exaone · updated 2025-03-18
EmoLlama-3-8B-Instruct-1048k-8bit
mlx-community/EmoLlama-3-8B-Instruct-1048k-8bit
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2024-05-14
Evathene-v1.2-MLX-8Bit
from sophosympatheia/Evathene-v1.2
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+
updated 2025-01-23
Falcon-E-1B-Instruct-4bit
from tiiuae/Falcon-E-1B-Instruct
Params
814M
Weights
≈ 464 MB
Mac memory
8 GB+
falcon-llm-license · updated 2025-06-10
Falcon-H1-1.5B-Instruct-5bit
from tiiuae/Falcon-H1-1.5B-Instruct
Params
1.6B
Weights
≈ 1.1 GB
Mac memory
8 GB+
falcon-llm-license · updated 2025-09-26
Falcon3-10B-Instruct-3bit
from tiiuae/Falcon3-10B-Instruct
Params
10B
Weights
≈ 4.5 GB
Mac memory
8 GB+
falcon-llm-license · updated 2024-12-17
Falcon3-3B-Instruct-1.58bit
from tiiuae/Falcon3-3B-Instruct-1.58bit
Params
1.4B
Weights
≈ 2.2 GB
Mac memory
8 GB+
falcon-llm-license · updated 2025-06-10
Falcon3-7B-Instruct-1.58bit-6bit
from tiiuae/Falcon3-7B-Instruct-1.58bit
Params
1.8B
Weights
≈ 2.3 GB
Mac memory
8 GB+
falcon-llm-license · updated 2025-06-10
Gabliterated-Qwen3-0.6B-4bit
from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated-Dev
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-06-28
Gemma-2-9B-It-SPPO-Iter3-8bit
from UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
Params
9.2B
Weights
≈ 9.8 GB
Mac memory
16 GB+
gemma · updated 2025-07-22
INTELLECT-3-6bit
from PrimeIntellect/INTELLECT-3
Params
107B
Weights
≈ 86.8 GB
Mac memory
128 GB+
mit · updated 2025-11-27
INTELLECT-3-bf16
from PrimeIntellect/INTELLECT-3
Params
107B
Weights
≈ 214 GB
Mac memory
256 GB+
mit · updated 2025-11-27
IQuest-Coder-V1-7B-Base-8bit
mlx-community/IQuest-Coder-V1-7B-Base-8bit
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
updated 2026-03-25
IQuest-Coder-V1-7B-Instruct-8bit
mlx-community/IQuest-Coder-V1-7B-Instruct-8bit
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
updated 2026-03-25
IQuest-Coder-V1-7B-Thinking-mlx_8bit
from IQuestLab/IQuest-Coder-V1-7B-Thinking
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
iquestcoder · updated 2026-03-03
Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v3-bfloat16
from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v3
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
updated 2026-03-13
JoyAI-LLM-Flash-6bit
from jdopensource/JoyAI-LLM-Flash
Params
49B
Weights
≈ 39.8 GB
Mac memory
48 GB+
updated 2026-02-15
K-EXAONE-236B-A23B-5bit
from LGAI-EXAONE/K-EXAONE-236B-A23B
Params
237B
Weights
≈ 163 GB
Mac memory
192 GB+
k-exaone · updated 2026-01-06
K-EXAONE-236B-A23B-8bit
from LGAI-EXAONE/K-EXAONE-236B-A23B
Params
237B
Weights
≈ 251 GB
Mac memory
512 GB+
k-exaone · updated 2026-01-06
KwaiCoder-AutoThink-preview-4bit
from Kwaipilot/KwaiCoder-AutoThink-preview
Params
41B
Weights
≈ 22.8 GB
Mac memory
32 GB+
kwaipilot-license · updated 2025-06-09
LFM2.5-1.2B-Base-4bit
from LiquidAI/LFM2.5-1.2B-Base
Params
1.2B
Weights
≈ 659 MB
Mac memory
8 GB+
other · updated 2026-01-06
Llama-SEA-LION-v3.5-8B-R-mlx-4bit
from aisingapore/Llama-SEA-LION-v3-8B-IT
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+
llama3.1 · updated 2025-09-10
Meta-Llama-Guard-2-8B-8bit
mlx-community/Meta-Llama-Guard-2-8B-8bit
Params
4.3B
Weights
≈ 5.0 GB
Mac memory
8 GB+
llama3 · updated 2024-04-18
MiniCPM4.1-8B-bf16
from openbmb/MiniCPM4.1-8B
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-09-08
Phi-3-small-8k-instruct-aq4_64
mlx-community/Phi-3-small-8k-instruct-aq4_64
Params
7.4B
Weights
≈ 29.6 GB
Mac memory
48 GB+
mit · updated 2024-05-24
Qwen-SEA-LION-v4-32B-IT-bf16
from aisingapore/Qwen-SEA-LION-v4-32B-IT
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
updated 2026-02-21
Qwen2-Math-1.5B-Instruct-bf16
mlx-community/Qwen2-Math-1.5B-Instruct-bf16
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-08-09
Qwen2-Math-72B-Instruct-bf16
mlx-community/Qwen2-Math-72B-Instruct-bf16
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+
tongyi-qianwen · updated 2024-08-09
Qwen2.5-Math-72B-Instruct-bf16
from Qwen/Qwen2.5-Math-72B
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+
qwen · updated 2024-09-19
Qwen3-0.6B-gabliterated-6bit
from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated
Params
596M
Weights
≈ 484 MB
Mac memory
8 GB+
updated 2026-01-06
Qwen3-30B-4bit-DWQ-053125
from Qwen/Qwen3-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-06-02
Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr2e-7
from Qwen/Qwen3-30B-A3B-Instruct-2507
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-07-31
Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr3e-8
from Qwen/Qwen3-30B-A3B-Instruct-2507
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-07-31
RakutenAI-7B-instruct-MLX-4bit
from Rakuten/RakutenAI-7B-instruct
Params
7.4B
Weights
≈ 4.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-03-20
ReZero-v0.1-llama-3.2-3b-it-grpo-250404-8bit
from Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+
updated 2025-04-16
Ring-flash-linear-2.0-4bit
from inclusionAI/Ring-flash-linear-2.0
Params
104B
Weights
≈ 58.6 GB
Mac memory
96 GB+
mit · updated 2025-10-17
Seed-Coder-8B-Reasoning-bf16-mlx-fp16
from ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16
Params
8.3B
Weights
≈ 16.5 GB
Mac memory
24 GB+
mit · updated 2025-07-18
SmolLM-360M-fp16
mlx-community/SmolLM-360M-fp16
Params
362M
Weights
≈ 724 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-07-16
SmolLM3-3B-gabliterated-bf16
from HuggingFaceTB/SmolLM3-3B
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-07-10
gemma-2-9b-it-SimPO-mixed-3-6-bit
from princeton-nlp/gemma-2-9b-it-SimPO
Params
9.2B
Weights
≈ 7.5 GB
Mac memory
16 GB+
mit · updated 2025-07-22
granite-4.0-1b-base-8bit
from ibm-granite/granite-4.0-1b-base
Params
1.6B
Weights
≈ 1.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
granite-4.1-8b-5bit
from ibm-granite/granite-4.1-8b
Params
8.4B
Weights
≈ 5.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-05-03
h2o-danube-1.8b-chat-4bit-mlx
mlx-community/h2o-danube-1.8b-chat-4bit-mlx
Params
1.8B
Weights
≈ 1.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-01-31
karakuri-lm-8x7b-instruct-v0.1-4bit
from karakuri-ai/karakuri-lm-8x7b-instruct-v0.1
Params
47B
Weights
≈ 26.3 GB
Mac memory
32 GB+
apache-2.0 · updated 2024-10-11
lille-130m-instruct-6bit
from mlx-community/lille-130m-instruct-fp16
Params
127M
Weights
≈ 103 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-09-05
mallam-5b-20k-instructions-v2-mxfp4
from mesolitica/mallam-5b-20k-instructions-v2
Params
5.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+
updated 2026-06-04
Llama-3-70B-Instruct-Gradient-262k-8bit
mlx-community/Llama-3-70B-Instruct-Gradient-262k-8bit
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+
llama3 · updated 2024-05-04