Mellum2-12B-A2.5B-Thinking-6bit
from JetBrains/Mellum2-12B-A2.5B-Thinking
Params
12B
Weights
≈ 9.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-08-11
Apple silicon
Apple MLX models
5,841 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
2,922 builds · page 36 of 49 · clear filters
Nanbeige4.1-3B-heretic-4bit
from Daizee/Nanbeige4.1-3B-heretic
Params
3.9B
Weights
≈ 2.2 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-02-16
OLMoE-1B-7B-0125-6bit
from allenai/OLMoE-1B-7B-0125
Params
6.9B
Weights
≈ 5.6 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-05
Olmo-3-7B-Instruct-SFT-4bit
from allenai/Olmo-3-7B-Instruct-SFT
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-11-20
Qwen2.5-Math-1.5B-Instruct-8bit
from Qwen/Qwen2.5-Math-1.5B
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-09-18
Qwen3-0.6B-gabliterated-8bit
from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+
updated 2026-01-06
SWE-Fixer-Editor-72B-4bit
from internlm/SWE-Fixer-Editor-72B
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+
mit · updated 2025-01-19
SmallThinker-3B-Preview-6bit
from Tiiny/SmallThinker-3B-Preview
Params
3.1B
Weights
≈ 2.5 GB
Mac memory
8 GB+
updated 2025-02-27
Teuken-7B-instruct-v0.6-4bit-mlx
from openGPT-X/Teuken-7B-instruct-v0.6
Params
7.5B
Weights
≈ 4.2 GB
Mac memory
8 GB+
cc-by-nc-4.0 · updated 2026-03-20
Trinity-Large-Thinking-4bit
from arcee-ai/Trinity-Large-Thinking
Params
399B
Weights
≈ 224 GB
Mac memory
256 GB+
apache-2.0 · updated 2026-04-02
Yi-9B-q
mlx-community/Yi-9B-q
Params
8.8B
Weights
≈ 34.8 GB
Mac memory
48 GB+
yi-license · updated 2024-03-06
deepcogito-cogito-v1-preview-qwen-32B-8bit
from deepcogito/cogito-v1-preview-qwen-32B
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-04-09
gemma-2-27b-bf16-8bit
from google/gemma-2-27b
Params
27B
Weights
≈ 28.9 GB
Mac memory
48 GB+
gemma · updated 2024-10-22
gemma-4-E2B-it-qat-assistant-5bit
from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
Params
78M
Weights
≈ 54 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
gemma-4-E4B-it-CEVRL-8bit
mlx-community/gemma-4-E4B-it-CEVRL-8bit
Params
7.5B
Weights
≈ 7.9 GB
Mac memory
16 GB+
updated 2026-06-16
granite-4.0-1b-5bit
from ibm-granite/granite-4.0-1b
Params
1.6B
Weights
≈ 1.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
granite-4.0-350m-5bit
from ibm-granite/granite-4.0-350m
Params
352M
Weights
≈ 242 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
llama2-70b-qnt4bit
mlx-community/llama2-70b-qnt4bit
Params
69B
Weights
≈ 275 GB
Mac memory
512 GB+
updated 2024-04-08
phi-4-abliterated-6bit
from huihui-ai/phi-4-abliterated
Params
15B
Weights
≈ 11.9 GB
Mac memory
16 GB+
mit · updated 2025-01-09
sarvam-m-8bit
from sarvamai/sarvam-m
Params
24B
Weights
≈ 25.0 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-05-27
shisa-v2-qwen2.5-32b-8bit
from shisa-ai/shisa-v2-qwen2.5-32b
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-04-14
simplescaling-s1-32B-fp16
from simplescaling/s1-32B
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-02-11
Qwen3-235B-A22B-Thinking-2507-4bit-DWQ
from Qwen/Qwen3-235B-A22B-Thinking-2507
Params
235B
Weights
≈ 132 GB
Mac memory
192 GB+
apache-2.0 · updated 2025-07-27
Hunyuan-A13B-Instruct-5bit
from tencent/Hunyuan-A13B-Instruct
Params
80B
Weights
≈ 55.3 GB
Mac memory
64 GB+
tencent-hunyuan-a13b · updated 2025-07-04
TenyxChat-7B-v1-4bit-mlx
mlx-community/TenyxChat-7B-v1-4bit-mlx
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2024-01-16
Phi-3-small-8k-instruct-AQ4_32
mlx-community/Phi-3-small-8k-instruct-AQ4_32
Params
7.4B
Weights
≈ 29.6 GB
Mac memory
48 GB+
mit · updated 2024-05-31
sunfall-nemomix-unleashed-12b-v0.6.1-8bit
from mistralai/Mistral-Nemo-Instruct-2407
Params
3.4B
Weights
≈ 4.0 GB
Mac memory
8 GB+
updated 2025-02-22
Deductive-Reasoning-Qwen-32B-MLX-4bit
from OpenPipe/Deductive-Reasoning-Qwen-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
mit · updated 2025-03-11
KernelLLM-6bit
from facebook/KernelLLM
Params
8.0B
Weights
≈ 6.5 GB
Mac memory
16 GB+
other · updated 2025-05-23
LongCat-Flash-Lite-4bit-DWQ
from meituan-longcat/LongCat-Flash-Lite
Params
69B
Weights
≈ 38.6 GB
Mac memory
48 GB+
mit · updated 2026-01-30
MiniCPM4.1-8B-8bit
from openbmb/MiniCPM4.1-8B
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-09-08
Olmo-3.1-32B-Instruct-bf16
from allenai/Olmo-3.1-32B-Instruct
Params
32B
Weights
≈ 64.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-12-23
Orchestrator-8B-6bit
from nvidia/Nemotron-Orchestrator-8B
Params
8.2B
Weights
≈ 6.7 GB
Mac memory
16 GB+
updated 2025-11-29
UserLM-8b-8bit
from microsoft/UserLM-8b
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
mit · updated 2025-10-09
gemma-3-270m-8bit
from google/gemma-3-270m
Params
436M
Weights
≈ 463 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
granite-4.1-8b-mxfp4
from ibm-granite/granite-4.1-8b
Params
8.4B
Weights
≈ 4.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-05-03
orpheus-3b-0.1-pretrained-8bit
from canopylabs/orpheus-3b-0.1-pretrained
Params
3.3B
Weights
≈ 3.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-04-02
Anubis-70B-v1.1-4bit
from TheDrummer/Anubis-70B-v1.1
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+
updated 2025-06-28
Apertus-8B-2509-bf16
from swiss-ai/Apertus-8B-2509
Params
8.1B
Weights
≈ 16.1 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-09-03
CalmeRys-78B-Orpo-v0.1-4bit
from dfurman/CalmeRys-78B-Orpo-v0.1
Params
78B
Weights
≈ 43.9 GB
Mac memory
64 GB+
mit · updated 2024-10-20
Evathene-v1.3-MLX-3Bit
from sophosympatheia/Evathene-v1.3
Params
73B
Weights
≈ 31.8 GB
Mac memory
48 GB+
updated 2025-01-25
Falcon-H1-0.5B-Instruct-6bit
from tiiuae/Falcon-H1-0.5B-Instruct
Params
521M
Weights
≈ 424 MB
Mac memory
8 GB+
falcon-llm-license · updated 2025-09-26
Falcon-H1-Tiny-Tool-Calling-90M-bf16
from tiiuae/Falcon-H1-Tiny-Tool-Calling-90M
Params
91M
Weights
≈ 182 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon-H1R-7B-5bit
from tiiuae/Falcon-H1R-7B
Params
7.6B
Weights
≈ 5.2 GB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-05
Huihui-LFM2.5-1.2B-Instruct-abliterated-4bit
from huihui-ai/Huihui-LFM2.5-1.2B-Instruct-abliterated
Params
1.2B
Weights
≈ 659 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-01-26
Hunyuan-7B-Instruct-2508-8bit
from tencent/Hunyuan-7B-Instruct
Params
7.5B
Weights
≈ 8.0 GB
Mac memory
16 GB+
updated 2025-08-04
IQuest-Coder-V1-7B-Base-Stage1-8bit
mlx-community/IQuest-Coder-V1-7B-Base-Stage1-8bit
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
updated 2026-03-25
Jan-v1-4B-bf16
from janhq/Jan-v1-4B
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-08-13
Josiefied-Hermes-3-Llama-3.2-3B-v1-bf16
from Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
Params
3.2B
Weights
≈ 6.4 GB
Mac memory
16 GB+
updated 2025-10-28
KwaiCoder-AutoThink-preview-6bit
from Kwaipilot/KwaiCoder-AutoThink-preview
Params
41B
Weights
≈ 33.0 GB
Mac memory
48 GB+
kwaipilot-license · updated 2025-06-10
MiniMax-M2.1-REAP-30-4bit
from 0xSero/MiniMax-M2.1-162B
Params
162B
Weights
≈ 91.1 GB
Mac memory
128 GB+
apache-2.0 · updated 2026-01-14
Olmo-3-7B-Instruct-bf16
from allenai/Olmo-3-7B-Instruct
Params
7.3B
Weights
≈ 14.6 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-11-20
OpenMath-Nemotron-32B-4bit
from nvidia/OpenMath-Nemotron-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
cc-by-4.0 · updated 2025-04-27
OpenMath-Nemotron-7B-4bit
from nvidia/OpenMath-Nemotron-7B
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
cc-by-4.0 · updated 2025-04-24
OpenR1-Distill-7B-4bit
from open-r1/OpenR1-Distill-7B
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-05-27
Pearl-7B
from louisbrulenaudet/Pearl-7B-0211-ties
Params
7.2B
Weights
≈ 28.7 GB
Mac memory
48 GB+
updated 2024-07-11
Phi-3-medium-4k-instruct-8bit
mlx-community/Phi-3-medium-4k-instruct-8bit
Params
14B
Weights
≈ 14.8 GB
Mac memory
24 GB+
mit · updated 2024-07-11
Qwen1.5-110B-8bit
mlx-community/Qwen1.5-110B-8bit
Params
111B
Weights
≈ 118 GB
Mac memory
192 GB+
tongyi-qianwen · updated 2024-04-26
Qwen3-4B-4bit-DWQ-calibration-1332
from Qwen/Qwen3-4B
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-05-11
Qwen3-4B-Sky-High-Hermes-4bit
from ZeroXClem/Qwen3-4B-Sky-High-Hermes
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-01-19