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 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

5,842 builds · page 47 of 98

whisper-large-v2-mlx-8bit

mlx-community/whisper-large-v2-mlx-8bit
8-bit
Uncategorised ↓ 60 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2024-03-09

whisper-medium-malayalam-mlx

from vrclc/Whisper-medium-Malayalam
Speech recognition · vrclc ↓ 60 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-08-22

whisper-small-asr-6bit

mlx-community/whisper-small-asr-6bit
6-bit
Speech recognition ↓ 60 · ♥ 0
Params
241M
Weights
≈ 199 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-15

OpenELM-3B

mlx-community/OpenELM-3B
Text generation ↓ 59 · ♥ 8
Params
3.0B
Weights
≈ 6.1 GB
Mac memory
16 GB+

updated 2024-04-26

GLM-4.5-Air-3bit-DWQ

from zai-org/GLM-4.5-Air
3-bit DWQ
Text generation · zai-org ↓ 59 · ♥ 4
Params
107B
Weights
≈ 46.8 GB
Mac memory
64 GB+

mit · updated 2025-07-29

QwQ-32B-Preview-4bit

from Qwen/QwQ-32B-Preview
4-bit
Text generation · Qwen ↓ 59 · ♥ 3
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-11-27

dolphin-2.9.3-qwen2-1.5b-8bit

from Qwen/Qwen2-1.5B
8-bit
Uncategorised · Qwen ↓ 59 · ♥ 3
Params
434M
Weights
≈ 507 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-06-14

internlm3-8b-instruct-4bit

from internlm/internlm3-8b-instruct
4-bit
Uncategorised · InternLM ↓ 59 · ♥ 3
Params
8.8B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-15

Bernini-R-bf16

from ByteDance/Bernini-R-Diffusers
bf16
Text to video · ByteDance ↓ 59 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-06-04

Fara1.5-9B-8bit

from microsoft/Fara1.5-9B
8-bit
Vision + text · Microsoft · Phi ↓ 59 · ♥ 2
Params
9.4B
Weights
≈ 10.4 GB
Mac memory
16 GB+

mit · updated 2026-07-29

Qwen2-72B-Instruct-4bit

mlx-community/Qwen2-72B-Instruct-4bit
4-bit
Text generation ↓ 59 · ♥ 2
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

tongyi-qianwen · updated 2024-06-07

Qwen2-VL-2B-Instruct-8bit

mlx-community/Qwen2-VL-2B-Instruct-8bit
8-bit
Vision + text ↓ 59 · ♥ 2
Params
2.2B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-24

SmolLM-135M-Instruct-fp16

mlx-community/SmolLM-135M-Instruct-fp16
fp16
Text generation ↓ 59 · ♥ 2
Params
135M
Weights
≈ 269 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-07-16

SmolLM3-3B-3bit

from HuggingFaceTB/SmolLM3-3B
3-bit
Text generation · Hugging Face ↓ 59 · ♥ 2
Params
3.1B
Weights
≈ 1.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-08

sarvam-translate-mlx-4bit

from sarvamai/sarvam-translate
4-bit
Text generation · sarvamai ↓ 59 · ♥ 2
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+

gpl-3.0 · updated 2025-06-19

Athene-V2-Chat-8bit

from Nexusflow/Athene-V2-Chat
8-bit
Text generation · Nexusflow ↓ 59 · ♥ 1
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+

other · updated 2024-11-16

II-Medical-8B-bf16

from Intelligent-Internet/II-Medical-8B
bf16
Text generation · Intelligent-Internet ↓ 59 · ♥ 1
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+

updated 2025-06-04

LFM2-350M-MLX

from LiquidAI/LFM2-350M
Text generation · LiquidAI ↓ 59 · ♥ 1
Params
354M
Weights
≈ 709 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-09-30

Ling-mini-2.0-2bit-DWQ

from inclusionAI/Ling-mini-2.0
2-bit DWQ
Text generation · inclusionAI ↓ 59 · ♥ 1
Params
16B
Weights
≈ 5.1 GB
Mac memory
8 GB+

mit · updated 2025-09-22

MiniMax-M2.7-8bit

from MiniMaxAI/MiniMax-M2.7
8-bit
Text generation · MiniMaxAI ↓ 59 · ♥ 1
Params
229B
Weights
≈ 243 GB
Mac memory
512 GB+

modified-mit · updated 2026-04-12

Mistralai-8B-Diagnosis-QA

mlx-community/Mistralai-8B-Diagnosis-QA
Text generation ↓ 59 · ♥ 1
Params
7.2B
Weights
≈ 29.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-03-16

Molmo-7B-D-0924-bf16

from Qwen/Qwen2-7B
bf16
Vision + text · Qwen ↓ 59 · ♥ 1
Params
8.0B
Weights
≈ 16.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-01-01

Soprano-1.1-80M-5bit

from ekwek/Soprano-1.1-80M
5-bit
Text to speech · ekwek ↓ 59 · ♥ 1
Params
110M
Weights
≈ 77 MB
Mac memory
8 GB+

updated 2026-02-04

VisualQuality-R1-7B-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Reinforcement learning · Qwen ↓ 59 · ♥ 1
Params
—
Weights
—
Mac memory
—

mit · updated 2025-08-06

gemma-4-E4B-it-qat-assistant-mxfp4

from google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant
MXFP4
Text generation · Google · Gemma ↓ 59 · ♥ 1
Params
79M
Weights
≈ 45 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

gemma-4-e4b-5bit

from google/gemma-4-e4b
5-bit
Any to any · Google · Gemma ↓ 59 · ♥ 1
Params
8.0B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-04-03

3b-zh-pretrain-research_release-8bit

from meta-llama/Llama-3.2-3B-Instruct
8-bit
Text to speech · Meta · Llama ↓ 59 · ♥ 0
Params
3.3B
Weights
≈ 3.5 GB
Mac memory
8 GB+

llama3.2 · updated 2025-04-10

Fimbulvetr-11B-v2-8bit

from Sao10K/Fimbulvetr-11B-v2
8-bit
Uncategorised · Sao10K ↓ 59 · ♥ 0
Params
11B
Weights
≈ 11.4 GB
Mac memory
16 GB+

cc-by-nc-4.0 · updated 2024-10-20

GLM-4-32B-Base-0414-4bit

from zai-org/GLM-4-32B-Base-0414
4-bit
Text generation · zai-org ↓ 59 · ♥ 0
Params
33B
Weights
≈ 18.3 GB
Mac memory
24 GB+

mit · updated 2025-04-21

GLM-4-9B-0414-6bit

from zai-org/GLM-4-9B-0414
6-bit
Text generation · zai-org ↓ 59 · ♥ 0
Params
9.4B
Weights
≈ 7.6 GB
Mac memory
16 GB+

mit · updated 2025-04-17

Hunyuan-4B-Instruct-4bit

from tencent/Hunyuan-4B-Instruct
4-bit
Text generation · tencent ↓ 59 · ♥ 0
Params
4.2B
Weights
≈ 2.4 GB
Mac memory
8 GB+

updated 2025-08-04

Josiefied-Qwen3.5-0.8B-gabliterated-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Qwen3.5-0.8B-gabliterated-v1
4-bit
Text generation · Goekdeniz-Guelmez ↓ 59 · ♥ 0
Params
752M
Weights
≈ 424 MB
Mac memory
8 GB+

updated 2026-03-13

Qwen2.5-3B-8bit

mlx-community/Qwen2.5-3B-8bit
8-bit
Text generation ↓ 59 · ♥ 0
Params
3.1B
Weights
≈ 3.3 GB
Mac memory
8 GB+

qwen-research · updated 2024-09-18

Qwen3-4B-Instruct-2507-gabliterated-mxfp4

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
MXFP4
Text generation · Goekdeniz-Guelmez ↓ 59 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

updated 2026-01-06

Sky-T1-32B-Preview-4bit

from NovaSky-AI/Sky-T1-32B-Preview
4-bit
Text generation · NovaSky-AI ↓ 59 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-01-13

aya-expanse-8b-8bit

from CohereLabs/aya-expanse-8b
8-bit
Text generation · Cohere ↓ 59 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

updated 2025-04-29

belle-whisper-large-v3-turbo-zh-fp16

mlx-community/belle-whisper-large-v3-turbo-zh-fp16
fp16
Speech recognition ↓ 59 · ♥ 0
Params
807M
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

deepcogito-cogito-v1-preview-llama-8B-4bit

from deepcogito/cogito-v1-preview-llama-8B
4-bit
Text generation · deepcogito ↓ 59 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3.1 · updated 2025-04-08

Qwen1.5-110B-Chat-4bit

mlx-community/Qwen1.5-110B-Chat-4bit
4-bit
Text generation ↓ 58 · ♥ 5
Params
111B
Weights
≈ 62.6 GB
Mac memory
96 GB+

tongyi-qianwen · updated 2024-04-26

stable-code-instruct-3b-4bit

mlx-community/stable-code-instruct-3b-4bit
4-bit
Text generation ↓ 58 · ♥ 5
Params
2.8B
Weights
≈ 1.8 GB
Mac memory
8 GB+

other · updated 2024-03-25

Nanbeige4.1-3B-bf16

from Nanbeige/Nanbeige4.1-3B
bf16
Text generation · Nanbeige ↓ 58 · ♥ 3
Params
3.9B
Weights
≈ 7.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-02-11

Qwen3.6-27B-MTP-bf16

from Qwen/Qwen3.6-27B
bf16
Text generation · Qwen ↓ 58 · ♥ 3
Params
425M
Weights
≈ 849 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

gemma-4-e4b-6bit

from google/gemma-4-e4b
6-bit
Any to any · Google · Gemma ↓ 58 · ♥ 3
Params
8.0B
Weights
≈ 7.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-04-03

DeepHermes-3-Llama-3-8B-Preview-4Bit

from NousResearch/DeepHermes-3-Llama-3-8B-Preview
4-bit
Text generation · NousResearch ↓ 58 · ♥ 2
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3 · updated 2025-02-13

DeepSeek-V3-3bit-bf16

from deepseek-ai/DeepSeek-V3
3-bit
Uncategorised · DeepSeek ↓ 58 · ♥ 2
Params
671B
Weights
≈ 294 GB
Mac memory
512 GB+

updated 2025-01-05

LFM2.5-1.2B-Instruct-bf16

from LiquidAI/LFM2.5-1.2B-Instruct
bf16
Text generation · LiquidAI ↓ 58 · ♥ 2
Params
1.2B
Weights
≈ 2.3 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

Mistral-Small-3.1-24B-Instruct-2503-bf16

from mistralai/Mistral-Small-3.1-24B-Base-2503
bf16
Uncategorised · Mistral ↓ 58 · ♥ 2
Params
24B
Weights
≈ 48.0 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-03-19

Qwen2-VL-7B-Instruct-8bit

mlx-community/Qwen2-VL-7B-Instruct-8bit
8-bit
Vision + text ↓ 58 · ♥ 2
Params
8.3B
Weights
≈ 8.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-24

SongGeneration-v2-large-8bit

from tencent/SongGeneration
8-bit
Text to audio · tencent ↓ 58 · ♥ 2
Params
5.1B
Weights
≈ 5.4 GB
Mac memory
16 GB+

other · updated 2026-05-31

medgemma-1.5-4b-it-6bit

mlx-community/medgemma-1.5-4b-it-6bit
6-bit
Vision + text ↓ 58 · ♥ 2
Params
5.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

health-ai-developer-foundations · updated 2026-01-14

Hy-MT2-7B

from Tencent-Hunyuan/Hy-MT2-7B
Translation · Tencent-Hunyuan ↓ 58 · ♥ 1
Params
7.5B
Weights
≈ 15.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-05-31

Josiefied-Qwen3-4B-abliterated-v1-bf16

from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
bf16
Text generation · Goekdeniz-Guelmez ↓ 58 · ♥ 1
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2025-05-01

Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr1e-8

from Qwen/Qwen3-30B-A3B-Instruct-2507
6-bit DWQ
Text generation · Qwen ↓ 58 · ♥ 1
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-08-02

Qwen3-Next-80B-A3B-Thinking-6bit

from Qwen/Qwen3-Next-80B-A3B-Thinking
6-bit
Text generation · Qwen ↓ 58 · ♥ 1
Params
80B
Weights
≈ 64.7 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-09-13

Step-3.7-Flash-oQ3e

from stepfun-ai/Step-3.7-Flash
3-bit
Vision + text · stepfun-ai ↓ 58 · ♥ 1
Params
199B
Weights
≈ 87.5 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-07-19

functiongemma-270m-it-8bit

from google/functiongemma-270m-it
8-bit
Text generation · Google · Gemma ↓ 58 · ♥ 1
Params
268M
Weights
≈ 285 MB
Mac memory
8 GB+

gemma · updated 2025-12-18

qwen3.5-27b-claude-opus-8bit-text-only

mlx-community/qwen3.5-27b-claude-opus-8bit-text-only
8-bit
Text generation ↓ 58 · ♥ 1
Params
27B
Weights
≈ 28.6 GB
Mac memory
48 GB+

updated 2026-03-31