openchat-3.6-8b-20240522-8bit
from meta-llama/Meta-Llama-3-8B
Params
2.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+
llama3 · updated 2024-05-24
Apple silicon
Apple MLX models
5,842 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 21m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 40 of 49 · clear filters
INTELLECT-3-5bit
from PrimeIntellect/INTELLECT-3
Params
107B
Weights
≈ 73.5 GB
Mac memory
96 GB+
mit · updated 2025-11-27
Josiefied-LFM2.5-1.2B-Instruct-abliterated-6bit
from Goekdeniz-Guelmez/Josiefied-LFM2.5-1.2B-Instruct-abliterated
Params
1.2B
Weights
≈ 951 MB
Mac memory
8 GB+
updated 2026-01-26
LFM2-1.2B-5bit
from LiquidAI/LFM2-1.2B
Params
1.2B
Weights
≈ 805 MB
Mac memory
8 GB+
lfm1.0 · updated 2025-07-12
Luni_StarDust-12b-v2
from Luni/StarDust-12b-v2
Params
12B
Weights
≈ 13.0 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-10-12
MiniMax-M2.5-5bit
from MiniMaxAI/MiniMax-M2.5
Params
229B
Weights
≈ 157 GB
Mac memory
192 GB+
modified-mit · updated 2026-02-13
Pleias-RAG-350M-6-bit
from PleIAs/Pleias-RAG-350M
Params
353M
Weights
≈ 287 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-04-24
SERA-32B-4bit
from allenai/SERA-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-01-27
Step-3.5-Flash-bf16
from stepfun-ai/Step-3.5-Flash
Params
197B
Weights
≈ 394 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-02-14
c4ai-command-a-03-2025-6bit
from CohereLabs/c4ai-command-a-03-2025
Params
111B
Weights
≈ 90.2 GB
Mac memory
128 GB+
cc-by-nc-4.0 · updated 2025-03-18
granite-4.0-1b-base-5bit
from ibm-granite/granite-4.0-1b-base
Params
1.6B
Weights
≈ 1.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
miscii-14b-0218-4bit
from sthenno-com/miscii-14b-0218
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-10
ArrowCanaria-Llama-8B-RL-v0.1-MLX-4bit
from DataPilot/ArrowCanaria-Llama-8B-RL-v0.1
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3.3 · updated 2026-03-27
Cydonia-24B-v3.1-6bit
from TheDrummer/Cydonia-24B-v3.1
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+
updated 2025-06-25
DeepHermes-3-Llama-3-3B-Preview-MLX
from NousResearch/DeepHermes-3-Llama-3-3B-Preview
Params
3.2B
Weights
≈ 6.4 GB
Mac memory
16 GB+
llama3 · updated 2025-07-31
DeepHermes-3-Llama-3-8B-Preview-8bit
from NousResearch/DeepHermes-3-Llama-3-8B-Preview
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2025-03-14
DeepHermes-3-Llama-3-8B-Preview-bf16
from NousResearch/DeepHermes-3-Llama-3-8B-Preview
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3 · updated 2025-03-14
Dobby-Mini-Unhinged-Plus-Llama-3.1-8B-bf16
from SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3.1 · updated 2025-06-11
Falcon-H1-1.5B-Instruct-6bit
from tiiuae/Falcon-H1-1.5B-Instruct
Params
1.6B
Weights
≈ 1.3 GB
Mac memory
8 GB+
falcon-llm-license · updated 2025-09-26
Falcon-H1-Tiny-Multilingual-100M-Base-5bit
from tiiuae/Falcon-H1-Tiny-Multilingual-100M-Base
Params
108M
Weights
≈ 74 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon-H1-Tiny-R-0.6B-6bit
from tiiuae/Falcon-H1-Tiny-R-0.6B
Params
622M
Weights
≈ 506 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon3-3B-Instruct-8bit
from tiiuae/Falcon3-3B-Instruct
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+
falcon-llm-license · updated 2024-12-17
Jan-v1-edge-bf16
from janhq/Jan-v1-edge
Params
1.7B
Weights
≈ 3.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-09-04
LLaDA2.0-mini-6bit
from inclusionAI/LLaDA2.0-mini
Params
16B
Weights
≈ 13.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-11-26
Llama-3-8B-UltraMedical-4bit
from TsinghuaC3I/Llama-3-8B-UltraMedical
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3 · updated 2025-06-03
Llama-3-Karamaru-v1
from SakanaAI/Llama-3-Karamaru-v1
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3 · updated 2025-04-01
LongCat-Flash-Thinking-ZigZag-6bit
from meituan-longcat/LongCat-Flash-Thinking-ZigZag
Params
561B
Weights
≈ 456 GB
Mac memory
512 GB+
mit · updated 2026-01-27
MiniCPM4.1-8B-6bit
from openbmb/MiniCPM4.1-8B
Params
8.2B
Weights
≈ 6.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-09-08
Nex-N2-mini-4bit
from nex-agi/Nex-N2-mini
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-06-08
OpenMath-Nemotron-1.5B-4bit
from nvidia/OpenMath-Nemotron-1.5B
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+
cc-by-4.0 · updated 2025-04-24
OpenThinker3-7B-8bit
from open-thoughts/OpenThinker3-7B
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-06-05
Orchestrator-8B-5bit
from nvidia/Nemotron-Orchestrator-8B
Params
8.2B
Weights
≈ 5.6 GB
Mac memory
16 GB+
updated 2025-11-29
Phi-4-reasoning-bf16
from microsoft/Phi-4-reasoning
Params
15B
Weights
≈ 29.3 GB
Mac memory
48 GB+
mit · updated 2025-05-01
Qwen2-1.5B-8bit
mlx-community/Qwen2-1.5B-8bit
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-06
Qwen3-0.6B-gabliterated-bf16
from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+
updated 2026-01-06
Qwen3-4B-Thinking-2507-gabliterated-6bit
from Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
updated 2026-01-17
RakutenAI-2.0-8x7B-MLX-8bit
from Rakuten/RakutenAI-2.0-8x7B
Params
47B
Weights
≈ 49.8 GB
Mac memory
64 GB+
apache-2.0 · updated 2026-03-20
RakutenAI-7B-chat-MLX-8bit
from Rakuten/RakutenAI-7B-chat
Params
7.4B
Weights
≈ 7.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-20
TeleChat3-36B-Thinking-4bit
from Tele-AI/TeleChat3-36B-Thinking
Params
36B
Weights
≈ 20.4 GB
Mac memory
32 GB+
updated 2026-01-19
Tessa-T1-32B-mlx-4bit
from Tesslate/Tessa-T1-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-25
Tessa-T1-3B-mlx-bf16
from Tesslate/Tessa-T1-3B
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-25
Tmax-9B-MLX-bf16
from allenai/tmax-9b
Params
9.0B
Weights
≈ 17.9 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-06-25
Virtuoso-Lite-3bit
from arcee-ai/Virtuoso-Lite
Params
10B
Weights
≈ 4.5 GB
Mac memory
8 GB+
other · updated 2025-01-30
Virtuoso-Lite-4bit
from arcee-ai/Virtuoso-Lite
Params
10B
Weights
≈ 5.8 GB
Mac memory
16 GB+
other · updated 2025-01-30
Virtuoso-Medium-v2-6bit
from arcee-ai/Virtuoso-Medium-v2
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-01-30
Yi-6B-200K-q
mlx-community/Yi-6B-200K-q
Params
6.1B
Weights
≈ 23.7 GB
Mac memory
32 GB+
yi-license · updated 2024-03-05
deepcogito-cogito-v1-preview-llama-3B-8bit
from deepcogito/cogito-v1-preview-llama-3B
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+
llama3.2 · updated 2025-04-08
deepcogito-cogito-v1-preview-qwen-32B-fp16
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-1.1-2b-it-bf16
from google/gemma-1.1-2b-it
Params
2.5B
Weights
≈ 5.0 GB
Mac memory
8 GB+
gemma · updated 2025-07-30
gemma-3-1b-it-qat-6bit
from google/gemma-3-1b-it
Params
1.3B
Weights
≈ 1.1 GB
Mac memory
8 GB+
gemma · updated 2025-04-18
gemma-3-270m-it-qat-8bit
from google/gemma-3-270m-it-qat-q4_0-unquantized
Params
436M
Weights
≈ 463 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
gemma-4-E2B-it-qat-assistant-6bit
from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
Params
78M
Weights
≈ 64 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
gemma-4-E4B-it-CEVRL
mlx-community/gemma-4-E4B-it-CEVRL
Params
7.5B
Weights
≈ 14.9 GB
Mac memory
24 GB+
updated 2026-06-16
granite-prisma-ft
mlx-community/granite-prisma-ft
Params
352M
Weights
≈ 883 MB
Mac memory
8 GB+
updated 2026-01-10
royallab_MN-LooseCannon-12B-v2
from royallab/MN-LooseCannon-12B-v2
Params
12B
Weights
≈ 13.0 GB
Mac memory
24 GB+
updated 2024-10-12
shisa-v2.1-unphi4-14b-mlx-8bit
from shisa-ai/shisa-v2.1-unphi4-14b
Params
15B
Weights
≈ 15.6 GB
Mac memory
24 GB+
mit · updated 2025-12-16
simplescaling-s1.1-32B-4bit
from simplescaling/s1.1-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-02-16
LLaDA2.0-flash-4bit
from inclusionAI/LLaDA2.0-flash
Params
103B
Weights
≈ 57.9 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-11-25
JoyAI-LLM-Flash-8bit
from jdopensource/JoyAI-LLM-Flash
Params
49B
Weights
≈ 52.0 GB
Mac memory
64 GB+
updated 2026-02-15
Llama-3-Smaug-8B-4bit
mlx-community/Llama-3-Smaug-8B-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama2 · updated 2024-04-21