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 2h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

5,841 builds · page 36 of 98

3b-de-ft-research_release-8bit

from canopylabs/orpheus-3b-0.1-pretrained
8-bit
Text to speech · canopylabs ↓ 94 · ♥ 0
Params
3.3B
Weights
≈ 3.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-09

HeartCodec-oss-fp16

from HeartMuLa/HeartCodec-oss-20260123
fp16
Text to audio · HeartMuLa ↓ 94 · ♥ 0
Params
1.6B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-02

Kumru-2B-4bit

from vngrs-ai/Kumru-2B
4-bit
Text generation · vngrs-ai ↓ 94 · ♥ 0
Params
2.4B
Weights
≈ 1.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-15

Nanonets-OCR2-3B-bf16

from Qwen/Qwen2.5-VL-3B-Instruct
bf16
Vision + text · Qwen ↓ 94 · ♥ 0
Params
3.8B
Weights
≈ 7.5 GB
Mac memory
16 GB+

updated 2025-10-14

YuE2-3B-bf16

from m-a-p/YuE2-3B
bf16
Text to audio · m-a-p ↓ 94 · ♥ 0
Params
3.6B
Weights
≈ 7.3 GB
Mac memory
16 GB+

cc-by-nc-4.0 · updated 2026-10-28

Phi-3.5-mini-instruct-8bit

mlx-community/Phi-3.5-mini-instruct-8bit
8-bit
Text generation ↓ 93 · ♥ 6
Params
3.8B
Weights
≈ 4.1 GB
Mac memory
8 GB+

mit · updated 2024-08-24

perplexity-ai-r1-1776-4bit

from perplexity-ai/r1-1776
4-bit
Uncategorised · perplexity-ai ↓ 93 · ♥ 6
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+

mit · updated 2025-02-25

Llama-3.2-1B-Instruct-MLXTuned

from meta-llama/Llama-3.2-1B-Instruct
Text generation · Meta · Llama ↓ 93 · ♥ 5
Params
1.2B
Weights
≈ 2.5 GB
Mac memory
8 GB+

llama3.2 · updated 2025-01-02

GLM-4.6V-Flash-mxfp4

from zai-org/GLM-4.6V-Flash
MXFP4
Vision + text · zai-org ↓ 93 · ♥ 3
Params
10B
Weights
≈ 7.1 GB
Mac memory
16 GB+

mit · updated 2026-02-21

SmolLM3-3B-Base-4bit

from HuggingFaceTB/SmolLM3-3B-Base
4-bit
Text generation · Hugging Face ↓ 93 · ♥ 3
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-09

dolphin-2.9.2-qwen2-7b-4bit

from Qwen/Qwen2-7B
4-bit
Uncategorised · Qwen ↓ 93 · ♥ 3
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-07-06

DeepSeek-R1-Distill-Qwen-32B-Q

from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
4-bit
Text generation · DeepSeek ↓ 93 · ♥ 2
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

mit · updated 2025-06-23

LFM2-700M-8bit

from LiquidAI/LFM2-700M
8-bit
Text generation · LiquidAI ↓ 93 · ♥ 2
Params
742M
Weights
≈ 789 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-07-11

Step-3.5-Flash-8bit

from stepfun-ai/Step-3.5-Flash
8-bit
Text generation · stepfun-ai ↓ 93 · ♥ 2
Params
197B
Weights
≈ 209 GB
Mac memory
256 GB+

apache-2.0 · updated 2026-02-04

DeepSeek-V4-Flash-mxfp4

mlx-community/DeepSeek-V4-Flash-mxfp4
MXFP4
Text generation ↓ 93 · ♥ 1
Params
284B
Weights
≈ 160 GB
Mac memory
192 GB+

updated 2026-04-25

Qwen2.5-14B-4bit

mlx-community/Qwen2.5-14B-4bit
4-bit
Text generation ↓ 93 · ♥ 1
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-09-18

sarashina2.2-3b-instruct-v0.1-4bit

from sbintuitions/sarashina2.2-3b-instruct-v0.1
4-bit
Text generation · sbintuitions ↓ 93 · ♥ 1
Params
3.4B
Weights
≈ 1.9 GB
Mac memory
8 GB+

mit · updated 2025-03-05

3b-fr-pretrain-research_release-6bit

from meta-llama/Llama-3.2-3B-Instruct
6-bit
Text to speech · Meta · Llama ↓ 93 · ♥ 0
Params
3.3B
Weights
≈ 2.7 GB
Mac memory
8 GB+

llama3.2 · updated 2025-04-09

GLM-4.5V-4bit

mlx-community/GLM-4.5V-4bit
4-bit
Uncategorised ↓ 93 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-08-11

GLM-4.7-Flash-bf16

from zai-org/GLM-4.7-Flash
bf16
Text generation · zai-org ↓ 93 · ♥ 0
Params
30B
Weights
≈ 59.9 GB
Mac memory
96 GB+

mit · updated 2026-01-25

HeartCodec-oss-fp32

from HeartMuLa/HeartCodec-oss-20260123
fp32
Text to audio · HeartMuLa ↓ 93 · ♥ 0
Params
1.6B
Weights
≈ 6.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-11-02

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

from Goekdeniz-Guelmez/Josiefied-Health-Qwen3-8B-abliterated-v1
8-bit
Text generation · Goekdeniz-Guelmez ↓ 93 · ♥ 0
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+

updated 2025-06-03

Qwen2.5-7B-8bit

mlx-community/Qwen2.5-7B-8bit
8-bit
Text generation ↓ 93 · ♥ 0
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-09-18

Qwen3-VL-Reranker-2B-bf16

from Qwen/Qwen3-VL-2B-Instruct
bf16
Reranking · Qwen ↓ 93 · ♥ 0
Params
2.1B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-14

d1a-e4b-8bit

from JohnP1/d1a-e4b
8-bit
Text classification · JohnP1 ↓ 93 · ♥ 0
Params
7.5B
Weights
≈ 7.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-25

gemma-2-27b-bf16-4bit

from google/gemma-2-27b
4-bit
Text generation · Google · Gemma ↓ 93 · ♥ 0
Params
27B
Weights
≈ 15.3 GB
Mac memory
24 GB+

gemma · updated 2024-10-22

Dia-1.6B-6bit

from nari-labs/Dia-1.6B
6-bit
Text to speech · nari-labs ↓ 92 · ♥ 10
Params
1.6B
Weights
≈ 3.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-24

gemma-4-12B-mxfp4

from google/gemma-4-12B
MXFP4
Any to any · Google · Gemma ↓ 92 · ♥ 4
Params
12B
Weights
≈ 6.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-06-03

Qwen3.5-27B-6bit

mlx-community/Qwen3.5-27B-6bit
6-bit
Vision + text ↓ 92 · ♥ 3
Params
27B
Weights
≈ 22.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-02-24

S1-mini-MLX-bf16

from superwhisper/s1-mini
bf16
Text generation · superwhisper ↓ 92 · ♥ 3
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+

s1-mini-license · updated 2026-08-20

GLM-4.6V-Flash-8bit

mlx-community/GLM-4.6V-Flash-8bit
8-bit
Vision + text ↓ 92 · ♥ 2
Params
—
Weights
—
Mac memory
—

mit · updated 2025-12-08

LFM2.5-2.6B-nvfp4

from LiquidAI/LFM2.5-2.6B
4-bit
Text generation · LiquidAI ↓ 92 · ♥ 1
Params
2.7B
Weights
≈ 1.5 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

deepseek-vl2-6bit

mlx-community/deepseek-vl2-6bit
6-bit
Vision + text ↓ 92 · ♥ 1
Params
27B
Weights
≈ 22.5 GB
Mac memory
32 GB+

deepseek · updated 2024-12-22

HeartMuLa-oss-3B-8bit

from HeartMuLa/HeartMuLa-oss-3B-happy-new-year
8-bit
Text to audio · HeartMuLa ↓ 92 · ♥ 0
Params
3.9B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-02

LFM2.5-2.6B-mxfp8

from LiquidAI/LFM2.5-2.6B
MXFP8
Text generation · LiquidAI ↓ 92 · ♥ 0
Params
2.7B
Weights
≈ 2.9 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

Mistral-7B-Instruct-v0.3-mlx-4Bit

from mistralai/Mistral-7B-Instruct-v0.3
4-bit
Uncategorised · Mistral ↓ 92 · ♥ 0
Params
7.2B
Weights
≈ 4.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-27

deepseek-vl2-tiny-8bit

mlx-community/deepseek-vl2-tiny-8bit
8-bit
Vision + text ↓ 92 · ♥ 0
Params
3.4B
Weights
≈ 3.7 GB
Mac memory
8 GB+

deepseek · updated 2024-12-22

svara-tts-v1-8bit

from kenpath/svara-tts-v1
8-bit
Text to speech · kenpath ↓ 92 · ♥ 0
Params
3.3B
Weights
≈ 3.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-26

gemma-3n-E4B-it-lm-bf16

from google/gemma-3n-E4B-it
bf16
Text generation · Google · Gemma ↓ 91 · ♥ 5
Params
6.9B
Weights
≈ 13.7 GB
Mac memory
24 GB+

gemma · updated 2025-06-29

LongCat-Flash-Lite-4bit

from meituan-longcat/LongCat-Flash-Lite
4-bit
Text generation · meituan-longcat ↓ 91 · ♥ 4
Params
69B
Weights
≈ 38.6 GB
Mac memory
48 GB+

mit · updated 2026-01-29

Qwen3-30B-A3B-bf16

from Qwen/Qwen3-30B-A3B
bf16
Text generation · Qwen ↓ 91 · ♥ 2
Params
31B
Weights
≈ 61.1 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-04-28

Qwen3-VL-8B-Instruct-6bit

mlx-community/Qwen3-VL-8B-Instruct-6bit
6-bit
Vision + text ↓ 91 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

c4ai-command-r-08-2024-4bit

mlx-community/c4ai-command-r-08-2024-4bit
4-bit
Text generation ↓ 91 · ♥ 2
Params
32B
Weights
≈ 18.2 GB
Mac memory
24 GB+

cc-by-nc-4.0 · updated 2024-08-31

diffusiongemma-26B-A4B-it-bf16

from google/diffusiongemma-26B-A4B-it
bf16
Vision + text · Google · Gemma ↓ 91 · ♥ 2
Params
26B
Weights
≈ 51.6 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-07-15

Josiefied-Qwen3-14B-abliterated-v3-bf16

from Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
bf16
Text generation · Goekdeniz-Guelmez ↓ 91 · ♥ 1
Params
15B
Weights
≈ 59.1 GB
Mac memory
96 GB+

updated 2025-06-04

LFM2.5-1.2B-Instruct-8bit

from LiquidAI/LFM2.5-1.2B-Instruct
8-bit
Text generation · LiquidAI ↓ 91 · ♥ 1
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

deepseek-vl2-tiny-6bit

mlx-community/deepseek-vl2-tiny-6bit
6-bit
Vision + text ↓ 91 · ♥ 1
Params
3.4B
Weights
≈ 2.9 GB
Mac memory
8 GB+

deepseek · updated 2024-12-22

CodeLlama-7b-Python-hf-4bit-mlx

mlx-community/CodeLlama-7b-Python-hf-4bit-mlx
4-bit
Text generation ↓ 91 · ♥ 0
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-01-04

ERNIE-4.5-0.3B-PT-bf16-ft

from baidu/ERNIE-4.5-0.3B-PT
bf16
Text generation · baidu ↓ 91 · ♥ 0
Params
361M
Weights
≈ 721 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-13

Ministral-3-3B-Base-2512-8bit

from mistralai/Ministral-3-3B-Base-2512
8-bit
Vision + text · Mistral ↓ 91 · ♥ 0
Params
3.8B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-18

Qwen3-VL-4B-Thinking-4bit

mlx-community/Qwen3-VL-4B-Thinking-4bit
4-bit
Vision + text ↓ 91 · ♥ 0
Params
4.4B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

VyvoTTS-EN-Beta-4bit

mlx-community/VyvoTTS-EN-Beta-4bit
4-bit
Text to speech ↓ 91 · ♥ 0
Params
1.8B
Weights
≈ 1.0 GB
Mac memory
8 GB+

updated 2025-12-20

Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx

mlx-community/Mixtral-8x7B-Instruct-v0.1-hf-4bit-mlx
4-bit
Uncategorised ↓ 90 · ♥ 7
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-01-15

Agents-A1-6bit

from InternScience/Agents-A1
6-bit
Vision + text · InternScience ↓ 90 · ♥ 4
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-01

Meta-Llama-3.1-70B-bf16

mlx-community/Meta-Llama-3.1-70B-bf16
bf16
Text generation ↓ 90 · ♥ 4
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+

llama3.1 · updated 2024-07-23

Ornith-1.0-35B-OptiQ-6bit

from ornith-ai/Ornith-1.0-35B
6-bit
Vision + text · ornith-ai ↓ 90 · ♥ 3
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

mit · updated 2026-09-15

DeepSeek-V4-Flash-mxfp8

mlx-community/DeepSeek-V4-Flash-mxfp8
MXFP8
Text generation ↓ 90 · ♥ 2
Params
284B
Weights
≈ 302 GB
Mac memory
512 GB+

updated 2026-04-25

MeloTTS-English-MLX

from myshell-ai/MeloTTS-English
Text to speech · myshell-ai ↓ 90 · ♥ 2
Params
52M
Weights
≈ 207 MB
Mac memory
8 GB+

mit · updated 2026-04-01