IQuest-Coder-V1-7B-Thinking-8bit
mlx-community/IQuest-Coder-V1-7B-Thinking-8bit
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
updated 2026-03-18
Apple silicon
Apple MLX models
5,842 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 47m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 43 of 49 · clear filters
LLaDA2.0-mini-8bit
from inclusionAI/LLaDA2.0-mini
Params
16B
Weights
≈ 17.3 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-11-26
Laguna-M.1-nvfp4
from poolside/Laguna-M.1
Params
226B
Weights
≈ 127 GB
Mac memory
192 GB+
apache-2.0 · updated 2026-06-18
Laguna-XS.2-bf16
from poolside/Laguna-XS.2
Params
33B
Weights
≈ 66.9 GB
Mac memory
96 GB+
apache-2.0 · updated 2026-04-28
LongCat-Flash-Chat-bf16
from meituan-longcat/LongCat-Flash-Chat
Params
561B
Weights
≈ 1122 GB
Mac memory
> 512 GB
mit · updated 2025-09-06
LongCat-Next-6bit
from meituan-longcat/LongCat-Next
Params
69B
Weights
≈ 55.7 GB
Mac memory
96 GB+
mit · updated 2026-03-30
MiniMax-M2.1-mxfp4
from MiniMaxAI/MiniMax-M2.1
Params
229B
Weights
≈ 129 GB
Mac memory
192 GB+
modified-mit · updated 2026-02-11
Nova-Tempus-70B-v0.1-MLX-4Bit
from sophosympatheia/Nova-Tempus-70B-v0.1
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+
llama3.3 · updated 2025-01-26
Nova-Tempus-70B-v0.1-MLX-6Bit
from sophosympatheia/Nova-Tempus-70B-v0.1
Params
71B
Weights
≈ 57.3 GB
Mac memory
96 GB+
llama3.3 · updated 2025-01-27
Qwen2-7B-4bit
mlx-community/Qwen2-7B-4bit
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-06
Qwen2-Math-7B-Instruct-4bit
mlx-community/Qwen2-Math-7B-Instruct-4bit
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-08-09
Qwen2-Math-7B-Instruct-bf16
mlx-community/Qwen2-Math-7B-Instruct-bf16
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-08-09
Qwen2.5-7B-Medicine-3bit
from WangCa/Qwen2.5-7B-Medicine
Params
7.6B
Weights
≈ 3.3 GB
Mac memory
8 GB+
mit · updated 2025-06-14
Step-3.7-Flash-6bit
from stepfun-ai/Step-3.7-Flash
Params
197B
Weights
≈ 160 GB
Mac memory
192 GB+
apache-2.0 · updated 2026-05-29
TeleChat3-36B-Thinking-6bit
from Tele-AI/TeleChat3-36B-Thinking
Params
36B
Weights
≈ 29.4 GB
Mac memory
48 GB+
updated 2026-01-19
TeleChat3-36B-Thinking-bf16
from Tele-AI/TeleChat3-36B-Thinking
Params
36B
Weights
≈ 72.5 GB
Mac memory
96 GB+
updated 2026-01-20
Tmax-27B-MLX-4bit
from allenai/tmax-27b
Params
27B
Weights
≈ 15.1 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-06-25
Tmax-27B-MLX-6bit
from allenai/tmax-27b
Params
27B
Weights
≈ 21.9 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-06-25
Trinity-Large-Thinking-5bit
from arcee-ai/Trinity-Large-Thinking
Params
399B
Weights
≈ 274 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-04-02
deepcogito-cogito-v1-preview-llama-3B-6bit
from deepcogito/cogito-v1-preview-llama-3B
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+
llama3.2 · updated 2025-04-08
deepcogito-cogito-v1-preview-qwen-32B-bf16
from deepcogito/cogito-v1-preview-qwen-32B
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-04-09
gemma-2-2b-fp16
mlx-community/gemma-2-2b-fp16
Params
2.6B
Weights
≈ 5.2 GB
Mac memory
8 GB+
gemma · updated 2024-07-31
gemma-4-E4B-it-qat-assistant-mxfp8
from google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant
Params
79M
Weights
≈ 84 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
granite-4.0-h-1b-3bit
from ibm-granite/granite-4.0-h-1b
Params
1.5B
Weights
≈ 641 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
h2o-danube2-1.8b-base-4bit
mlx-community/h2o-danube2-1.8b-base-4bit
Params
1.8B
Weights
≈ 1.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-04-09
karakuri-lm-8x7b-instruct-v0.1-8bit
from karakuri-ai/karakuri-lm-8x7b-instruct-v0.1
Params
47B
Weights
≈ 49.6 GB
Mac memory
64 GB+
apache-2.0 · updated 2024-10-11
lil-bard
from N8Programs/lil-bard
Params
172M
Weights
≈ 344 MB
Mac memory
8 GB+
updated 2026-08-26
reim-ai-chat-mlx
mlx-community/reim-ai-chat-mlx
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2024-02-14
talkie-box-4bit
mlx-community/talkie-box-4bit
Params
13B
Weights
≈ 8.0 GB
Mac memory
16 GB+
updated 2026-04-30
Youtu-LLM-2B-mlx-4bit
from tencent/Youtu-LLM-2B
Params
2.0B
Weights
≈ 1.1 GB
Mac memory
8 GB+
other · updated 2026-01-03
deepcogito-cogito-v1-preview-llama-8B-bf16
from deepcogito/cogito-v1-preview-llama-8B
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3.1 · updated 2025-04-08
Hermes-2-Theta-Llama-3-8B-8bit
from NousResearch/Hermes-2-Pro-Llama-3-8B
Params
2.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-14
Qwen3-235B-A22B-Thinking-2507-mixed-3-5bit
from Qwen/Qwen3-235B-A22B-Thinking-2507
Params
235B
Weights
≈ 162 GB
Mac memory
192 GB+
apache-2.0 · updated 2025-07-25
Tanuki-8B-dpo-v1.0-8bit
mlx-community/Tanuki-8B-dpo-v1.0-8bit
Params
7.5B
Weights
≈ 8.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-08-30
Trinity-Large-Thinking-8bit
mlx-community/Trinity-Large-Thinking-8bit
Params
399B
Weights
≈ 424 GB
Mac memory
512 GB+
updated 2026-04-03
granite-4.0-350m-base-8bit
from ibm-granite/granite-4.0-350m-base
Params
352M
Weights
≈ 374 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
mamba-130m-hf-f32
from state-spaces/mamba-130m-hf
Params
129M
Weights
≈ 517 MB
Mac memory
8 GB+
updated 2025-08-28
miscii-14b-0218-6bit
from sthenno-com/miscii-14b-0218
Params
15B
Weights
≈ 12.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-10
Agatha-111B-v1-8bit
from TheDrummer/Agatha-111B-v1
Params
111B
Weights
≈ 118 GB
Mac memory
192 GB+
updated 2025-06-12
Cydonia-24B-v3.1-bf16
from TheDrummer/Cydonia-24B-v3.1
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+
updated 2025-06-25
EXAONE-Deep-7.8B-fp16
from LGAI-EXAONE/EXAONE-Deep-7.8B
Params
7.8B
Weights
≈ 15.6 GB
Mac memory
24 GB+
exaone · updated 2025-03-18
Falcon-H1-Tiny-90M-Base-6bit
from tiiuae/Falcon-H1-Tiny-90M-Base
Params
91M
Weights
≈ 74 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon-H1-Tiny-90M-Instruct-6bit
from tiiuae/Falcon-H1-Tiny-90M-Instruct
Params
91M
Weights
≈ 74 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon-H1-Tiny-R-0.6B-8bit
from tiiuae/Falcon-H1-Tiny-R-0.6B
Params
622M
Weights
≈ 662 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon-H1-Tiny-R-0.6B-pre-GRPO-6bit
from tiiuae/Falcon-H1-Tiny-R-0.6B-pre-GRPO
Params
622M
Weights
≈ 506 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon-H1-Tiny-R-90M-bf16
from tiiuae/Falcon-H1-Tiny-R-90M
Params
91M
Weights
≈ 182 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon3-1B-Instruct-1.58bit-6bit
from tiiuae/Falcon3-1B-Instruct-1.58bit
Params
401M
Weights
≈ 719 MB
Mac memory
8 GB+
falcon-llm-license · updated 2025-06-10
IQuest-Coder-V1-14B-Base-8bit
mlx-community/IQuest-Coder-V1-14B-Base-8bit
Params
14B
Weights
≈ 15.3 GB
Mac memory
24 GB+
updated 2026-03-25
IQuest-Coder-V1-14B-Thinking-mlx_8bit
from IQuestLab/IQuest-Coder-V1-14B-Thinking
Params
14B
Weights
≈ 15.3 GB
Mac memory
24 GB+
iquestcoder · updated 2026-03-03
Josiefied-LFM2.5-1.2B-Instruct-abliterated-mxfp4
from Goekdeniz-Guelmez/Josiefied-LFM2.5-1.2B-Instruct-abliterated
Params
1.2B
Weights
≈ 2.3 GB
Mac memory
8 GB+
updated 2026-01-26
Josiefied-Qwen3-0.6B-gabliterated-bfloat16
from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-gabliterated-v1
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+
updated 2026-01-26
Laguna-M.1-5bit
from poolside/Laguna-M.1
Params
226B
Weights
≈ 155 GB
Mac memory
192 GB+
apache-2.0 · updated 2026-06-18
Laguna-M.1-8bit
from poolside/Laguna-M.1
Params
226B
Weights
≈ 240 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-06-18
Llama-3-Smaug-8B-8bit
mlx-community/Llama-3-Smaug-8B-8bit
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
llama2 · updated 2024-04-21
Llama-3-Swallow-8B-Instruct-v0.1-8bit
mlx-community/Llama-3-Swallow-8B-Instruct-v0.1-8bit
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2024-07-01
LongCat-Next-8bit
from meituan-longcat/LongCat-Next
Params
69B
Weights
≈ 72.8 GB
Mac memory
96 GB+
mit · updated 2026-03-30
Lucie-7B-Instruct-4bit
from OpenLLM-France/Lucie-7B-Instruct
Params
6.7B
Weights
≈ 3.8 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-01-17
MiniMax-M2.1-REAP-30-5bit
from 0xSero/MiniMax-M2.1-162B
Params
162B
Weights
≈ 111 GB
Mac memory
128 GB+
apache-2.0 · updated 2026-01-14
Monad-bf16
from PleIAs/Monad
Params
57M
Weights
≈ 113 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-11-10
Nex-N2-Pro-mlx-8bit
from nex-agi/Nex-N2-Pro
Params
396B
Weights
≈ 421 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-06-15