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 13 of 98

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

from Qwen/Qwen3.5-35B-A3B
4-bit
Text generation · Qwen ↓ 621 · ♥ 4
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-30

ltx-2.5-mlx-q8

from Lightricks/LTX-2.5
8-bit
Text to video · Lightricks ↓ 621 · ♥ 3
Params
—
Weights
—
Mac memory
—

ltx-2-community-license-agreement · updated 2026-10-15

functiongemma-270m-it-4bit

from google/functiongemma-270m-it
4-bit
Text generation · Google · Gemma ↓ 619 · ♥ 3
Params
268M
Weights
≈ 151 MB
Mac memory
8 GB+

gemma · updated 2025-12-18

Falcon3-7B-Instruct-4bit

from tiiuae/Falcon3-7B-Instruct
4-bit
Text generation · TII · Falcon ↓ 619 · ♥ 0
Params
7.5B
Weights
≈ 4.2 GB
Mac memory
8 GB+

falcon-llm-license · updated 2024-12-17

llm-jp-4-8b-thinking-4bit

from llm-jp/llm-jp-4-8b-thinking
4-bit
Text generation · llm-jp ↓ 616 · ♥ 2
Params
8.6B
Weights
≈ 4.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-12

gemma-4-e4b-it-bf16

from google/gemma-4-E4B-it
bf16
Vision + text · Google · Gemma ↓ 609 · ♥ 8
Params
7.9B
Weights
≈ 15.9 GB
Mac memory
24 GB+

gemma · updated 2026-07-06

DeepSeek-V3.2-4bit

from deepseek-ai/DeepSeek-V3.2
4-bit
Text generation · DeepSeek ↓ 609 · ♥ 7
Params
672B
Weights
≈ 378 GB
Mac memory
512 GB+

mit · updated 2026-01-06

Qwen3-235B-A22B-Instruct-2507-8bit

from Qwen/Qwen3-235B-A22B-Instruct-2507
8-bit
Text generation · Qwen ↓ 609 · ♥ 2
Params
235B
Weights
≈ 250 GB
Mac memory
512 GB+

apache-2.0 · updated 2025-07-22

Dia-1.6B-fp16

from nari-labs/Dia-1.6B
fp16
Text to speech · nari-labs ↓ 606 · ♥ 3
Params
1.6B
Weights
≈ 3.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-27

Qwen3-Coder-30B-A3B-Instruct-bf16

from Qwen/Qwen3-Coder-30B-A3B-Instruct
bf16
Text generation · Qwen ↓ 606 · ♥ 2
Params
31B
Weights
≈ 61.1 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-08-01

Codestral-22B-v0.1-4bit

mlx-community/Codestral-22B-v0.1-4bit
4-bit
Uncategorised ↓ 602 · ♥ 14
Params
22B
Weights
≈ 12.5 GB
Mac memory
16 GB+

mnpl · updated 2024-05-29

Mistral-7B-v0.2-4bit

mlx-community/Mistral-7B-v0.2-4bit
4-bit
Uncategorised ↓ 602 · ♥ 8
Params
7.2B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2024-03-25

Ling-3.1-flash-1019-oQ4e-mtp

from inclusionAI/Ling-3.1-flash-1019
4-bit
Text generation · inclusionAI ↓ 601 · ♥ 0
Params
572B
Weights
≈ 322 GB
Mac memory
512 GB+

mit · updated 2026-10-28

DeepSeek-OCR-2-8bit

mlx-community/DeepSeek-OCR-2-8bit
8-bit
Vision + text ↓ 599 · ♥ 5
Params
3.4B
Weights
≈ 4.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-28

higgs-audio-v2-3B-mlx-q8

from bosonai/higgs-tts-2-3b-base
8-bit
Text to speech · bosonai ↓ 596 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-04-18

clef-8bit

from Cloudflare/clef
8-bit
Zero-shot classification · Cloudflare ↓ 594 · ♥ 9
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-10-07

Qwen3.5-4B-MTP-4bit

from Qwen/Qwen3.5-4B
4-bit
Text generation · Qwen ↓ 594 · ♥ 2
Params
121M
Weights
≈ 68 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

KAT-Coder-V2.5-Dev-OptiQ-4bit-REAP-18B

from mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit
4-bit
Text generation ↓ 593 · ♥ 8
Params
19B
Weights
≈ 10.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-15

multilingual-e5-small-mlx

mlx-community/multilingual-e5-small-mlx
Sentence similarity ↓ 593 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2024-01-11

Qwen3.8-27B-mxfp8

from Qwen/Qwen3.8-27B
MXFP8
Vision + text · Qwen ↓ 591 · ♥ 10
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-11-11

Qwen3-Coder-480B-A35B-Instruct-8bit

from Qwen/Qwen3-Coder-480B-A35B-Instruct
8-bit
Text generation · Qwen ↓ 591 · ♥ 0
Params
480B
Weights
≈ 510 GB
Mac memory
> 512 GB

apache-2.0 · updated 2025-12-08

gpt-oss-120b-4bit

mlx-community/gpt-oss-120b-4bit
4-bit
Text generation ↓ 589 · ♥ 10
Params
117B
Weights
≈ 15.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-08-06

K2-Horizon-MoVA-36B-A4B-4bit

from IFM/K2-Horizon-MoVA-36B-A4B
4-bit
Text generation · IFM ↓ 586 · ♥ 4
Params
37B
Weights
≈ 21.1 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-09-29

K2-Horizon-3.7B-4bit

from IFM/K2-Horizon-3.7B
4-bit
Text generation · IFM ↓ 584 · ♥ 0
Params
5.1B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-30

Qwen3.5-0.8B-5bit

from Qwen/Qwen3.5-0.8B-Base
5-bit
Vision + text · Qwen ↓ 584 · ♥ 0
Params
853M
Weights
≈ 719 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-02

unsloth-gemma-4-26B-A4B-it-qat-oQ4

from unsloth/gemma-4-26B-A4B-it-qat-q4_0-unquantized
4-bit
Vision + text · unsloth ↓ 581 · ♥ 0
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-06-08

LFM2-8B-A1B-4bit

from LiquidAI/LFM2-8B-A1B
4-bit
Text generation · LiquidAI ↓ 577 · ♥ 10
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-10-08

gemma-1.1-2b-it-4bit

mlx-community/gemma-1.1-2b-it-4bit
4-bit
Text generation ↓ 577 · ♥ 3
Params
2.5B
Weights
≈ 2.2 GB
Mac memory
8 GB+

gemma · updated 2024-04-05

gemma-4-26B-A4B-it-qat-8bit

mlx-community/gemma-4-26B-A4B-it-qat-8bit
8-bit
Vision + text ↓ 577 · ♥ 3
Params
26B
Weights
≈ 28.0 GB
Mac memory
48 GB+

updated 2026-06-05

meta-llama-Llama-4-Scout-17B-16E-4bit

from meta-llama/Llama-4-Scout-17B-16E
4-bit
Text generation · Meta · Llama ↓ 573 · ♥ 10
Params
108B
Weights
≈ 60.6 GB
Mac memory
96 GB+

llama4 · updated 2025-04-06

embeddinggemma-300m-8bit

mlx-community/embeddinggemma-300m-8bit
8-bit
Sentence similarity ↓ 570 · ♥ 6
Params
308M
Weights
≈ 327 MB
Mac memory
8 GB+

gemma · updated 2025-09-04

bge-m3-mlx-4bit

from BAAI/bge-m3
4-bit
Embeddings · BAAI ↓ 569 · ♥ 1
Params
568M
Weights
≈ 320 MB
Mac memory
8 GB+

mit · updated 2026-03-16

Kimi-K2.7-Code-mlx-DQ3_K_M-q8

from moonshotai/Kimi-K2.7-Code
8-bit
Text generation · Moonshot · Kimi ↓ 568 · ♥ 5
Params
1.0T
Weights
≈ 1091 GB
Mac memory
> 512 GB

modified-mit · updated 2026-06-16

Unlimited-OCR-2-4bit

from baidu/Unlimited-OCR-2
4-bit
Vision + text · baidu ↓ 567 · ♥ 1
Params
3.3B
Weights
≈ 2.5 GB
Mac memory
8 GB+

mit · updated 2026-10-27

Qwen-Image-2512-3bit

from Qwen/Qwen-Image-2512
3-bit
Text to image · Qwen ↓ 566 · ♥ 3
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-01-01

MiniCPM-V-4.7-35B-A3B-nvfp4

from openbmb/MiniCPM-V-4.7-35B-A3B
4-bit
Vision + text · openbmb ↓ 564 · ♥ 2
Params
35B
Weights
≈ 23.5 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-13

IndexTTS-2-MLX

from IndexTeam/IndexTTS-2
Text to speech · IndexTeam ↓ 561 · ♥ 0
Params
—
Weights
—
Mac memory
—

other · updated 2026-08-31

Qwen3-30B-A3B-4bit-DWQ

from Qwen/Qwen3-30B-A3B
4-bit DWQ
Text generation · Qwen ↓ 559 · ♥ 30
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-05-05

Qwen3-8B-bf16

from Qwen/Qwen3-8B
bf16
Text generation · Qwen ↓ 559 · ♥ 1
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-04-28

K2-Horizon-7B-4bit

from IFM/K2-Horizon-7B
4-bit
Text generation · IFM ↓ 555 · ♥ 1
Params
9.0B
Weights
≈ 5.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-30

MiniMax-M3-4bit

from MiniMaxAI/MiniMax-M3
4-bit
Vision + text · MiniMaxAI ↓ 554 · ♥ 7
Params
427B
Weights
≈ 241 GB
Mac memory
512 GB+

minimax-community · updated 2026-06-20

Qwen3-14B-6bit

from Qwen/Qwen3-14B
6-bit
Text generation · Qwen ↓ 553 · ♥ 1
Params
15B
Weights
≈ 12.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-04-28

Qwen3-VL-4B-Instruct-8bit

mlx-community/Qwen3-VL-4B-Instruct-8bit
8-bit
Vision + text ↓ 551 · ♥ 3
Params
4.4B
Weights
≈ 5.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

flint-oQ6e

from RecursiveSI/flint
6-bit
Text generation · RecursiveSI ↓ 551 · ♥ 0
Params
40B
Weights
≈ 32.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-10-27

granite-4.1-8b-8bit

from ibm-granite/granite-4.1-8b
8-bit
Text generation · IBM · Granite ↓ 549 · ♥ 2
Params
8.4B
Weights
≈ 8.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-05-03

Ternary-Bonsai-2-4B-2bit

from Qwen/Qwen3.5-4B
2-bit
Vision + text · Qwen ↓ 547 · ♥ 0
Params
4.5B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-15

Qwythos-9B-v2-OptiQ-4bit

from empero-ai/Qwythos-9B-v2
4-bit
Vision + text · empero-ai ↓ 546 · ♥ 3
Params
9.0B
Weights
≈ 6.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-30

MOSS-Music-8B-Thinking-4bit

from OpenMOSS-Team/MOSS-Music-8B-Thinking
4-bit
Audio + text · OpenMOSS-Team ↓ 546 · ♥ 0
Params
9.1B
Weights
≈ 6.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-06-28

ltx-2.5-mlx

from Lightricks/LTX-2.5
Text to video · Lightricks ↓ 543 · ♥ 5
Params
—
Weights
—
Mac memory
—

ltx-2-community-license-agreement · updated 2026-10-15

gemma-4-26b-a4b-it-6bit

from google/gemma-4-26B-A4B-it
6-bit
Vision + text · Google · Gemma ↓ 541 · ♥ 7
Params
26B
Weights
≈ 21.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-05

Ling-3.1-flash-1019-oQ2e-mtp

from inclusionAI/Ling-3.1-flash-1019
2-bit
Text generation · inclusionAI ↓ 540 · ♥ 0
Params
572B
Weights
≈ 179 GB
Mac memory
256 GB+

mit · updated 2026-10-28

GLM-4.7-REAP-50-mxfp4

from 0xSero/GLM-4.7-185B
MXFP4
Text generation · 0xSero ↓ 537 · ♥ 29
Params
185B
Weights
≈ 104 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-01-03

GLM-4.5-Air-8bit

from zai-org/GLM-4.5-Air
8-bit
Text generation · zai-org ↓ 535 · ♥ 11
Params
107B
Weights
≈ 114 GB
Mac memory
192 GB+

mit · updated 2025-07-29

diffusiongemma-26B-A4B-it-OptiQ-4bit

from google/diffusiongemma-26B-A4B-it
4-bit
Vision + text · Google · Gemma ↓ 534 · ♥ 20
Params
25B
Weights
≈ 14.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-20

clef-omni-4bit

from Cloudflare/clef-omni
4-bit
Zero-shot classification · Cloudflare ↓ 534 · ♥ 6
Params
32B
Weights
≈ 19.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-09

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-mxfp4

from nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
MXFP4
Text generation · NVIDIA ↓ 534 · ♥ 5
Params
32B
Weights
≈ 17.8 GB
Mac memory
24 GB+

openmdw-1.1 · updated 2026-08-11

mel-roformer-kim-vocal-2-mlx

from KimberleyJSN/melbandroformer
Audio to audio · KimberleyJSN ↓ 533 · ♥ 10
Params
228M
Weights
≈ 456 MB
Mac memory
8 GB+

mit · updated 2026-05-01