Skip to content
AI Model Radar
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 7 of 49 · clear filters

OLMoE-1B-7B-0125-4bit

from allenai/OLMoE-1B-7B-0125
4-bit
Text generation · Ai2 · OLMo ↓ 438 · ♥ 1
Params
6.9B
Weights
≈ 3.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-05

tiny-aya-global-8bit-mlx

from CohereLabs/tiny-aya-global
8-bit
Text generation · Cohere ↓ 437 · ♥ 2
Params
3.3B
Weights
≈ 3.6 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2026-02-18

flint-oQ5e

from RecursiveSI/flint
5-bit
Text generation · RecursiveSI ↓ 436 · ♥ 0
Params
40B
Weights
≈ 27.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-10-27

GLM-5.3-mixed-4_5bit

from zai-org/GLM-5.3-BF16
5-bit
Text generation · zai-org ↓ 434 · ♥ 1
Params
743B
Weights
≈ 511 GB
Mac memory
> 512 GB

glm-5.3 · updated 2026-09-02

MiniCPM5-2B-chat-mlx-16bit

from openbmb/MiniCPM5-2B
16-bit
Text generation · openbmb ↓ 434 · ♥ 0
Params
2.5B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-14

Kimi-K2.7-Code-4bit

mlx-community/Kimi-K2.7-Code-4bit
4-bit
Text generation ↓ 431 · ♥ 6
Params
1.0T
Weights
≈ 578 GB
Mac memory
> 512 GB

updated 2026-06-12

flint-oQ3e

from RecursiveSI/flint
3-bit
Text generation · RecursiveSI ↓ 428 · ♥ 0
Params
40B
Weights
≈ 17.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-27

Spark-X2.5-4B-OptiQ-4bit

from XHToken/Spark-X2.5-4B
4-bit
Text generation · XHToken ↓ 427 · ♥ 3
Params
4.1B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-13

Qwen3-32B-8bit

from Qwen/Qwen3-32B
8-bit
Text generation · Qwen ↓ 422 · ♥ 1
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-04-28

DeepSeek-V4-Pro-4bit

mlx-community/DeepSeek-V4-Pro-4bit
4-bit
Text generation ↓ 421 · ♥ 5
Params
1.6T
Weights
≈ 885 GB
Mac memory
> 512 GB

updated 2026-04-25

Olmo-3-7B-Instruct-8bit

from allenai/Olmo-3-7B-Instruct
8-bit
Text generation · Ai2 · OLMo ↓ 415 · ♥ 2
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-20

JevK5-chat-mlx-8bit

from alibiserikbay/JevK5
8-bit
Text generation · alibiserikbay ↓ 411 · ♥ 1
Params
4.2B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-14

gemma-4-E4B-it-OBLITERATED-mlx-fp16

from OBLITERATUS/gemma-4-E4B-it-OBLITERATED
fp16
Text generation · OBLITERATUS ↓ 410 · ♥ 0
Params
7.5B
Weights
≈ 15.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-05-19

flint-oQ2e

from RecursiveSI/flint
2-bit
Text generation · RecursiveSI ↓ 406 · ♥ 1
Params
40B
Weights
≈ 12.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-27

Step-3.5-Flash-4bit

from stepfun-ai/Step-3.5-Flash
4-bit
Text generation · stepfun-ai ↓ 405 · ♥ 10
Params
197B
Weights
≈ 111 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-02-04

LFM2.5-24B-A2B-Preview-mxfp4

from lq-preview/LFM2.5-24B-A2B-Preview
MXFP4
Text generation · lq-preview ↓ 402 · ♥ 0
Params
24B
Weights
≈ 13.5 GB
Mac memory
24 GB+

lfm1.0 · updated 2026-10-13

Qwen3-Coder-Next-bf16

from Qwen/Qwen3-Coder-Next
bf16
Text generation · Qwen ↓ 400 · ♥ 3
Params
80B
Weights
≈ 159 GB
Mac memory
192 GB+

apache-2.0 · updated 2026-02-04

JevK5-chat-mlx-4bit

from alibiserikbay/JevK5
4-bit
Text generation · alibiserikbay ↓ 397 · ♥ 2
Params
4.2B
Weights
≈ 2.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-14

magnum-v4-72b-4bit

from anthracite-org/magnum-v4-72b
4-bit
Text generation · anthracite-org ↓ 397 · ♥ 1
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-12-14

Olmo-3.1-32B-Think-8bit

from allenai/Olmo-3.1-32B-Think
8-bit
Text generation · Ai2 · OLMo ↓ 395 · ♥ 0
Params
32B
Weights
≈ 34.2 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-12-24

LFM2.5-24B-A2B-Preview-4bit

from lq-preview/LFM2.5-24B-A2B-Preview
4-bit
Text generation · lq-preview ↓ 392 · ♥ 0
Params
24B
Weights
≈ 13.5 GB
Mac memory
24 GB+

lfm1.0 · updated 2026-10-13

flint-oQ2.7e

from RecursiveSI/flint
2-bit
Text generation · RecursiveSI ↓ 392 · ♥ 0
Params
40B
Weights
≈ 12.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-27

Dolphin-Mistral-24B-Venice-Edition-DWQ

from dphn/Dolphin-Mistral-24B-Venice-Edition
4-bit
Text generation · dphn ↓ 389 · ♥ 5
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-07

Nemotron-3-Super-120B-A12B-MLX-6bit

from nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
6-bit
Text generation · NVIDIA ↓ 379 · ♥ 4
Params
121B
Weights
≈ 98.1 GB
Mac memory
128 GB+

nvidia-open-model-license · updated 2026-03-31

gemma-4-E4B-it-qat-assistant-4bit

from google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant
4-bit
Text generation · Google · Gemma ↓ 377 · ♥ 1
Params
79M
Weights
≈ 45 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B

from mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit
4-bit
Text generation ↓ 376 · ♥ 4
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-30

flint-oQ2.5e

from RecursiveSI/flint
2-bit
Text generation · RecursiveSI ↓ 373 · ♥ 0
Params
40B
Weights
≈ 12.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-27

Laguna-XS-2.1-OptiQ-4bit

from poolside/Laguna-XS-2.1
4-bit
Text generation · poolside ↓ 371 · ♥ 3
Params
33B
Weights
≈ 18.8 GB
Mac memory
24 GB+

openmdw-1.1 · updated 2026-10-16

NVIDIA-Nemotron-3-Super-120B-A12B-OptiQ-2bit

from nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
2-bit
Text generation · NVIDIA ↓ 371 · ♥ 2
Params
121B
Weights
≈ 37.9 GB
Mac memory
48 GB+

nvidia-nemotron-open-model-license · updated 2026-09-15

Qwen3.8-27B-MTP-mxfp8

from Qwen/Qwen3.8-27B
MXFP8
Text generation · Qwen ↓ 365 · ♥ 8
Params
425M
Weights
≈ 451 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-11

K2-Horizon-7B-chat-mlx-16bit

from IFM/K2-Horizon-7B
16-bit
Text generation · IFM ↓ 361 · ♥ 0
Params
9.0B
Weights
≈ 18.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-14

Hy-Memory-30B-A3B-4bit

from tencent/Hy-Memory-30B-A3B
4-bit
Text generation · tencent ↓ 360 · ♥ 0
Params
30B
Weights
≈ 16.9 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-21

translategemma-27b-it-8bit

from google/translategemma-27b-it
8-bit
Text generation · Google · Gemma ↓ 359 · ♥ 5
Params
27B
Weights
≈ 28.7 GB
Mac memory
48 GB+

gemma · updated 2026-01-16

Ornith-1.0-9B-4bit

from ornith-ai/Ornith-1.0-9B
4-bit
Text generation · ornith-ai ↓ 356 · ♥ 10
Params
9.4B
Weights
≈ 6.0 GB
Mac memory
16 GB+

mit · updated 2026-06-28

LFM2-24B-A2B-4bit

from LiquidAI/LFM2-24B-A2B
4-bit
Text generation · LiquidAI ↓ 356 · ♥ 0
Params
24B
Weights
≈ 13.4 GB
Mac memory
24 GB+

lfm1.0 · updated 2026-02-25

MiniMax-M2.7-4bit

from MiniMaxAI/MiniMax-M2.7
4-bit
Text generation · MiniMaxAI ↓ 351 · ♥ 2
Params
229B
Weights
≈ 129 GB
Mac memory
192 GB+

modified-mit · updated 2026-04-12

Qwen3-8B-4bit-DWQ

from Qwen/Qwen3-8B
4-bit DWQ
Text generation · Qwen ↓ 351 · ♥ 2
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-05-01

Qwen3-Next-80B-A3B-Thinking-8bit

from Qwen/Qwen3-Next-80B-A3B-Thinking
8-bit
Text generation · Qwen ↓ 349 · ♥ 4
Params
80B
Weights
≈ 84.7 GB
Mac memory
128 GB+

apache-2.0 · updated 2025-09-13

Qwen3-8B-6bit

from Qwen/Qwen3-8B
6-bit
Text generation · Qwen ↓ 345 · ♥ 4
Params
8.2B
Weights
≈ 6.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-04-28

Nemotron-3-Ultra-550B-A55B-4bit

from nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
4-bit
Text generation · NVIDIA ↓ 341 · ♥ 5
Params
549B
Weights
≈ 313 GB
Mac memory
512 GB+

nvidia-open-model-license · updated 2026-06-05

gemma-4-26B-A4B-it-qat-q4_0-mlx-aligned

from google/gemma-4-26B-A4B-it-qat-q4_0-unquantized
4-bit
Text generation · Google · Gemma ↓ 341 · ♥ 3
Params
25B
Weights
≈ 14.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-06

Qwen3.8-27B-MTP-nvfp4

from Qwen/Qwen3.8-27B
4-bit
Text generation · Qwen ↓ 337 · ♥ 2
Params
425M
Weights
≈ 239 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-11

NVIDIA-Nemotron-Nano-9B-v2-6bit

from nvidia/NVIDIA-Nemotron-Nano-9B-v2
6-bit
Text generation · NVIDIA ↓ 337 · ♥ 1
Params
1.9B
Weights
≈ 1.9 GB
Mac memory
8 GB+

nvidia-open-model-license · updated 2025-09-05

Llama-3.2-3B-Fluxed

from VincentGOURBIN/Llama-3.2-3B-Fluxed
Text generation · VincentGOURBIN ↓ 336 · ♥ 3
Params
3.2B
Weights
≈ 6.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-12-03

Qwen-AgentWorld-35B-A3B-oQ4

from Qwen/Qwen-AgentWorld-35B-A3B
4-bit
Text generation · Qwen ↓ 335 · ♥ 13
Params
35B
Weights
≈ 19.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-06-27

NVIDIA-Nemotron-3-Nano-4B-OptiQ-4bit

from nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
4-bit
Text generation · NVIDIA ↓ 334 · ♥ 3
Params
4.0B
Weights
≈ 2.2 GB
Mac memory
8 GB+

nvidia-nemotron-open-model-license · updated 2026-09-14

Llama-Guard-3-1B-chat-mlx-16bit

from meta-llama/Llama-Guard-3-1B
16-bit
Text generation · Meta · Llama ↓ 334 · ♥ 0
Params
1.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+

llama3.2 · updated 2026-10-14

Apertus-8B-Instruct-2509-bf16

from swiss-ai/Apertus-8B-Instruct-2509
bf16
Text generation · swiss-ai ↓ 331 · ♥ 6
Params
8.1B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-09-03

LFM2.5-2.6B-OptiQ-4bit

from LiquidAI/LFM2.5-2.6B
4-bit
Text generation · LiquidAI ↓ 330 · ♥ 2
Params
2.7B
Weights
≈ 1.5 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-10-14

Qwen2.5-Coder-14B-Instruct-abliterated-6bit

from huihui-ai/Qwen2.5-Coder-14B-Instruct-abliterated
6-bit
Text generation · huihui-ai ↓ 324 · ♥ 0
Params
15B
Weights
≈ 12.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-02-22

Qwen2.5-Coder-7B-Instruct-3bit

from Qwen/Qwen2.5-Coder-7B-Instruct
3-bit
Text generation · Qwen ↓ 323 · ♥ 0
Params
7.6B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-14

GLM-4.5-Air-bf16

from zai-org/GLM-4.5-Air
bf16
Text generation · zai-org ↓ 322 · ♥ 0
Params
107B
Weights
≈ 214 GB
Mac memory
256 GB+

mit · updated 2025-10-07

LFM2-2.6B-Exp-4bit

from LiquidAI/LFM2-2.6B-Exp
4-bit
Text generation · LiquidAI ↓ 320 · ♥ 1
Params
2.6B
Weights
≈ 1.4 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-12-26

Huihui-Qwen3.5-35B-A3B-abliterated-6bit

from huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated
6-bit
Text generation · huihui-ai ↓ 315 · ♥ 4
Params
35B
Weights
≈ 28.2 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-03-04

Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-4-bit

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
4-bit
Text generation · Goekdeniz-Guelmez ↓ 315 · ♥ 3
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-08

Qwen2.5-Coder-14B-Instruct-bf16

from Qwen/Qwen2.5-Coder-14B-Instruct
bf16
Text generation · Qwen ↓ 315 · ♥ 2
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-11-11

ColGrep-Agent-2B-MLX-8bit

from lightonai/colgrep-agent-2B
8-bit
Text generation · lightonai ↓ 315 · ♥ 0
Params
2.5B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-19

Mellum2-12B-A2.5B-Thinking-4bit

from JetBrains/Mellum2-12B-A2.5B-Thinking
4-bit
Text generation · JetBrains ↓ 314 · ♥ 4
Params
12B
Weights
≈ 6.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-08-11