Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,842 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

5,842 builds · page 57 of 98

tasksource-ModernBERT-base-embed-6bit

from answerdotai/ModernBERT-base
6-bit
Sentence similarity · answerdotai ↓ 45 · ♥ 0
Params
149M
Weights
≈ 121 MB
Mac memory
8 GB+

updated 2025-04-02

WizardLM-2-8x22B-4bit

mlx-community/WizardLM-2-8x22B-4bit
4-bit
Uncategorised ↓ 44 · ♥ 9
Params
141B
Weights
≈ 79.4 GB
Mac memory
96 GB+

apache-2.0 · updated 2024-04-16

DeepScaleR-1.5B-6.5bit

from agentica-org/DeepScaleR-1.5B-Preview
5-bit
Text generation · agentica-org ↓ 44 · ♥ 4
Params
1.8B
Weights
≈ 1.2 GB
Mac memory
8 GB+

mit · updated 2025-02-17

bu-30b-a3b-preview-4bit

from browser-use/bu-30b-a3b-preview
4-bit
Vision + text · browser-use ↓ 44 · ♥ 4
Params
—
Weights
—
Mac memory
—

updated 2025-12-17

Nemotron-Cascade-2-30B-A3B-mlx-6bit

from nvidia/Nemotron-Cascade-2-30B-A3B
6-bit
Text generation · NVIDIA ↓ 44 · ♥ 3
Params
32B
Weights
≈ 25.7 GB
Mac memory
32 GB+

nvidia-open-model-license · updated 2026-03-20

Qwen1.5-32B-Chat-4bit

mlx-community/Qwen1.5-32B-Chat-4bit
4-bit
Text generation ↓ 44 · ♥ 3
Params
33B
Weights
≈ 19.4 GB
Mac memory
24 GB+

tongyi-qianwen · updated 2024-04-05

gemma-2-2b-jpn-it

from google/gemma-2-2b-it
Text generation · Google · Gemma ↓ 44 · ♥ 3
Params
2.6B
Weights
≈ 5.2 GB
Mac memory
8 GB+

gemma · updated 2024-10-03

gemma-4-e4b-mxfp8

from google/gemma-4-e4b
MXFP8
Any to any · Google · Gemma ↓ 44 · ♥ 2
Params
8.0B
Weights
≈ 9.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-04-03

CodeLlama-7b-Instruct-hf-4bit-mlx-2

from codellama/CodeLlama-7b-Instruct-hf
4-bit
Text generation · codellama ↓ 44 · ♥ 1
Params
6.7B
Weights
≈ 3.8 GB
Mac memory
8 GB+

llama2 · updated 2025-04-28

DeepHermes-3-Mistral-24B-Preview-4bit

from NousResearch/DeepHermes-3-Mistral-24B-Preview
4-bit
Text generation · NousResearch ↓ 44 · ♥ 1
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-14

Qwen2.5-14B-1M-YOYO-V2-Q4

from YOYO-AI/Qwen2.5-14B-YOYO-latest-V2
4-bit
Text generation · YOYO-AI ↓ 44 · ♥ 1
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-02-18

Qwen3-VL-32B-Thinking-8bit

mlx-community/Qwen3-VL-32B-Thinking-8bit
8-bit
Vision + text ↓ 44 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-21

Qwen3-VL-4B-Thinking-bf16

mlx-community/Qwen3-VL-4B-Thinking-bf16
bf16
Vision + text ↓ 44 · ♥ 1
Params
4.4B
Weights
≈ 8.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-10-14

Qwopus3.6-35B-A3B-Coder-bf16

from Jackrong/Qwopus3.6-35B-A3B-Coder
bf16
Vision + text · Jackrong ↓ 44 · ♥ 1
Params
35B
Weights
≈ 70.2 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-06-30

aya-23-8B-8bit

mlx-community/aya-23-8B-8bit
8-bit
Text generation ↓ 44 · ♥ 1
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

cc-by-nc-4.0 · updated 2024-05-23

gemma-4-12B-it-assistant-mxfp4

from google/gemma-4-12B-it-assistant
MXFP4
Any to any · Google · Gemma ↓ 44 · ♥ 1
Params
423M
Weights
≈ 238 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-03

granite-4.1-8b-nvfp4

from ibm-granite/granite-4.1-8b
4-bit
Text generation · IBM · Granite ↓ 44 · ♥ 1
Params
8.4B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-03

stable-code-3b-4bit

mlx-community/stable-code-3b-4bit
4-bit
Text generation ↓ 44 · ♥ 1
Params
2.8B
Weights
≈ 1.8 GB
Mac memory
8 GB+

other · updated 2024-03-18

swahili-gemma-1b-mlx-fp16

from CraneAILabs/swahili-gemma-1b
fp16
Text generation · CraneAILabs ↓ 44 · ♥ 1
Params
1.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+

gemma · updated 2025-08-26

AREX-Base-mixed-mxfp4-bf16

from BAAI/AREX-Base
MXFP4
Text generation · BAAI ↓ 44 · ♥ 0
Params
123B
Weights
≈ 78.4 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-07-29

AceReason-Nemotron-1.1-7B-bf16

from nvidia/AceReason-Nemotron-1.1-7B
bf16
Text generation · NVIDIA ↓ 44 · ♥ 0
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

nvidia-open-model-license · updated 2025-06-17

Bunny-Llama-3-8B-V-4bit

mlx-community/Bunny-Llama-3-8B-V-4bit
4-bit
Vision + text ↓ 44 · ♥ 0
Params
8.5B
Weights
≈ 4.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-07-04

Dolphin3.0-Llama3.1-8B-6bit

from dphn/Dolphin3.0-Llama3.1-8B
6-bit
Uncategorised · dphn ↓ 44 · ♥ 0
Params
8.0B
Weights
≈ 6.5 GB
Mac memory
16 GB+

llama3.1 · updated 2025-01-06

EuroLLM-22B-Instruct-2512-mlx-5bit

from utter-project/EuroLLM-22B-Instruct-2512
5-bit
Text generation · utter-project ↓ 44 · ♥ 0
Params
23B
Weights
≈ 15.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-12-16

Florence-2-base-ft-3bit

mlx-community/Florence-2-base-ft-3bit
3-bit
Vision + text ↓ 44 · ♥ 0
Params
271M
Weights
≈ 130 MB
Mac memory
8 GB+

mit · updated 2024-11-24

Florence-2-base-ft-6bit

mlx-community/Florence-2-base-ft-6bit
6-bit
Vision + text ↓ 44 · ♥ 0
Params
271M
Weights
≈ 229 MB
Mac memory
8 GB+

mit · updated 2024-11-24

Gemma-2-9B-It-SPPO-Iter3-mixed-4-6-bit

from UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
6-bit
Text generation · UCLA-AGI ↓ 44 · ♥ 0
Params
9.2B
Weights
≈ 7.5 GB
Mac memory
16 GB+

gemma · updated 2025-07-22

Gemma-SEA-LION-v4.5-E2B-IT-8bits

from aisingapore/Gemma-SEA-LION-v4.5-E2B-IT
8-bit
Text generation · aisingapore ↓ 44 · ♥ 0
Params
4.6B
Weights
≈ 4.9 GB
Mac memory
8 GB+

mit · updated 2026-06-21

Josiefied-Qwen3-1.7B-abliterated-v1-8bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-1.7B-abliterated-v1
8-bit
Text generation · Goekdeniz-Guelmez ↓ 44 · ♥ 0
Params
1.7B
Weights
≈ 1.8 GB
Mac memory
8 GB+

updated 2025-05-01

Laguna-M.1-mxfp4

from poolside/Laguna-M.1
MXFP4
Text generation · poolside ↓ 44 · ♥ 0
Params
226B
Weights
≈ 127 GB
Mac memory
192 GB+

apache-2.0 · updated 2026-06-18

Mellum2-12B-A2.5B-Thinking-bf16

from JetBrains/Mellum2-12B-A2.5B-Thinking
bf16
Text generation · JetBrains ↓ 44 · ♥ 0
Params
12B
Weights
≈ 24.3 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-08-11

Qwen3-0.6B-Base

from Qwen/Qwen3-0.6B-Base
Text generation · Qwen ↓ 44 · ♥ 0
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-27

Qwen3-4B-Sky-High-Hermes-gabliterated-bfloat16

from Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
Text generation · Goekdeniz-Guelmez ↓ 44 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2026-01-23

Qwen3-VL-32B-Instruct-bf16

mlx-community/Qwen3-VL-32B-Instruct-bf16
bf16
Vision + text ↓ 44 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-21

Qwen3-VL-Text-30B-A3B-Instruct-bf16

mlx-community/Qwen3-VL-Text-30B-A3B-Instruct-bf16
bf16
Text generation ↓ 44 · ♥ 0
Params
31B
Weights
≈ 61.1 GB
Mac memory
96 GB+

updated 2025-12-25

SmolVLM-500M-Instruct-6bit

from HuggingFaceTB/SmolLM2-360M-Instruct
6-bit
Vision + text · Hugging Face ↓ 44 · ♥ 0
Params
507M
Weights
≈ 413 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-23

aya-vision-32b-3bit

mlx-community/aya-vision-32b-3bit
3-bit
Vision + text ↓ 44 · ♥ 0
Params
33B
Weights
≈ 15.1 GB
Mac memory
24 GB+

cc-by-nc-4.0 · updated 2025-03-05

c4ai-command-r-plus-2bit

mlx-community/c4ai-command-r-plus-2bit
2-bit
Text generation ↓ 44 · ♥ 0
Params
104B
Weights
≈ 37.8 GB
Mac memory
48 GB+

cc-by-nc-4.0 · updated 2024-04-15

command-a-reasoning-08-2025-8bit

from CohereLabs/command-a-reasoning-08-2025
8-bit
Text generation · Cohere ↓ 44 · ♥ 0
Params
111B
Weights
≈ 118 GB
Mac memory
192 GB+

cc-by-nc-4.0 · updated 2025-08-26

gemma-3-1b-it-DQ

from google/gemma-3-1b-it
4-bit
Text generation · Google · Gemma ↓ 44 · ♥ 0
Params
1.3B
Weights
≈ 732 MB
Mac memory
8 GB+

gemma · updated 2025-06-15

gemma-4-31B-it-qat-assistant-6bit

from google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
6-bit
Text generation · Google · Gemma ↓ 44 · ♥ 0
Params
470M
Weights
≈ 382 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

llama3-8b-cpt-sahabatai-v1-instruct-4bit

from GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
4-bit
Text generation · GoToCompany ↓ 44 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3 · updated 2026-06-06

llm-jp-3-172b-beta1-instruct-4bit

mlx-community/llm-jp-3-172b-beta1-instruct-4bit
4-bit
Text generation ↓ 44 · ♥ 0
Params
172B
Weights
≈ 97.0 GB
Mac memory
128 GB+

llm-jp-3-172b-beta1-tou · updated 2024-09-18

llm-jp-3.1-8x13b-instruct4-8bit

from llm-jp/llm-jp-3.1-8x13b-instruct4
8-bit
Text generation · llm-jp ↓ 44 · ♥ 0
Params
73B
Weights
≈ 77.7 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-06-16

prometheus-7b-v2.0-8bit

mlx-community/prometheus-7b-v2.0-8bit
8-bit
Text generation ↓ 44 · ♥ 0
Params
7.2B
Weights
≈ 7.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-09-04

simplescaling-s1-32B-fp32

from simplescaling/s1-32B
fp32
Text generation · simplescaling ↓ 44 · ♥ 0
Params
33B
Weights
≈ 131 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-02-16

smallthinker-3b-preview-q8

from Tiiny/SmallThinker-3B-Preview
8-bit
Text generation · Tiiny ↓ 44 · ♥ 0
Params
3.1B
Weights
≈ 3.3 GB
Mac memory
8 GB+

updated 2025-01-05

whisper-small-8bit

from openai/whisper-small
8-bit
Speech recognition · OpenAI · gpt-oss ↓ 44 · ♥ 0
Params
241M
Weights
≈ 258 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

Nex-N2-mini-nvfp4

from nex-agi/Nex-N2-mini
4-bit
Text generation · nex-agi ↓ 43 · ♥ 8
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-06-08

Orchestrator-8B-8bit

from nvidia/Nemotron-Orchestrator-8B
8-bit
Text generation · NVIDIA ↓ 43 · ♥ 5
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+

updated 2025-11-29

JoyAI-LLM-Flash-4bit-DWQ

from jdopensource/JoyAI-LLM-Flash
4-bit DWQ
Text generation · jdopensource ↓ 43 · ♥ 4
Params
49B
Weights
≈ 27.6 GB
Mac memory
48 GB+

updated 2026-02-15

XortronCriminalComputingConfig-mlx-8Bit

from darkc0de/XortronCriminalComputingConfig
8-bit
Text generation · darkc0de ↓ 43 · ♥ 4
Params
24B
Weights
≈ 25.0 GB
Mac memory
32 GB+

wtfpl · updated 2025-06-19

NemotronLabs-VoiceChat-11B-mlx-bf16

from nvidia/NVIDIA-NemotronLabs-VoiceChat-11B
bf16
Uncategorised · NVIDIA ↓ 43 · ♥ 3
Params
11B
Weights
≈ 22.2 GB
Mac memory
32 GB+

openmdw-1.1 · updated 2026-08-05

OlympicCoder-7B-4bit

from open-r1/OlympicCoder-7B
4-bit
Text generation · open-r1 ↓ 43 · ♥ 3
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-12

Nanbeige4.1-3B-heretic-8bit

from Daizee/Nanbeige4.1-3B-heretic
8-bit
Text generation · Daizee ↓ 43 · ♥ 2
Params
3.9B
Weights
≈ 4.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-16

OpenSora-STDiT-v3

mlx-community/OpenSora-STDiT-v3
Uncategorised ↓ 43 · ♥ 2
Params
1.2B
Weights
≈ 2.4 GB
Mac memory
8 GB+

other · updated 2024-08-01