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 84 of 98

mallam-5b-20k-instructions-v2-8bit

from mesolitica/mallam-5b-20k-instructions-v2
8-bit
Text generation · mesolitica ↓ 22 · ♥ 0
Params
5.0B
Weights
≈ 5.3 GB
Mac memory
8 GB+

updated 2026-06-04

olmOCR-7B-0725-6bit

from Qwen/Qwen2.5-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 22 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-07-25

paligemma2-28b-mix-448-4bit

mlx-community/paligemma2-28b-mix-448-4bit
4-bit
Vision + text ↓ 22 · ♥ 0
Params
28B
Weights
≈ 16.1 GB
Mac memory
24 GB+

gemma · updated 2025-02-19

sapiens2-pointmap-0.4b-bf16

from facebook/sapiens2-pointmap-0.4b
bf16
Depth estimation · facebook ↓ 22 · ♥ 0
Params
529M
Weights
≈ 1.1 GB
Mac memory
8 GB+

sapiens2-license · updated 2026-09-13

sarashina2.1-1b-sft-8bit

from Aratako/sarashina2.1-1b-sft
8-bit
Text generation · Aratako ↓ 22 · ♥ 0
Params
1.4B
Weights
≈ 1.5 GB
Mac memory
8 GB+

other · updated 2024-12-11

whisper-large-v3-lv-late-cv19

mlx-community/whisper-large-v3-lv-late-cv19
Uncategorised ↓ 22 · ♥ 0
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

updated 2026-02-05

whisper-small.en-asr-6bit

mlx-community/whisper-small.en-asr-6bit
6-bit
Speech recognition ↓ 22 · ♥ 0
Params
241M
Weights
≈ 199 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-15

whisper-tiny.en-asr-4bit

mlx-community/whisper-tiny.en-asr-4bit
4-bit
Speech recognition ↓ 22 · ♥ 0
Params
37M
Weights
≈ 22 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-15

zipvoice-vietnamese

mlx-community/zipvoice-vietnamese
Text to speech ↓ 22 · ♥ 0
Params
123M
Weights
≈ 490 MB
Mac memory
8 GB+

updated 2026-04-04

EfRLFN-x4

from EvgeneyBogatyrev/EfRLFN
Image to image · EvgeneyBogatyrev ↓ 21 · ♥ 8
Params
504K
Weights
≈ 2 MB
Mac memory
8 GB+

mit · updated 2026-06-04

QVQ-72B-Preview-3bit

from Qwen/Qwen2-VL-72B
3-bit
Vision + text · Qwen ↓ 21 · ♥ 5
Params
73B
Weights
≈ 32.1 GB
Mac memory
48 GB+

qwen · updated 2024-12-24

talkie-box-8bit

mlx-community/talkie-box-8bit
8-bit
Text generation ↓ 21 · ♥ 3
Params
13B
Weights
≈ 14.4 GB
Mac memory
24 GB+

updated 2026-04-30

Master-Yi-9B-8bit

mlx-community/Master-Yi-9B-8bit
8-bit
Uncategorised ↓ 21 · ♥ 2
Params
8.8B
Weights
≈ 9.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-05-19

Qwen3-235B-A22B-4bit-DWQ-053125

from mlx-community/Qwen3-235B-A22B-8bit
4-bit DWQ
Text generation ↓ 21 · ♥ 2
Params
235B
Weights
≈ 132 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-06-03

WizardLM2-8x22B-4bit-mlx

mlx-community/WizardLM2-8x22B-4bit-mlx
4-bit
Text generation ↓ 21 · ♥ 2
Params
22B
Weights
≈ 19.0 GB
Mac memory
24 GB+

updated 2024-04-18

Cocktail-Fork-MRX-adapted-eq

mlx-community/Cocktail-Fork-MRX-adapted-eq
Audio to audio ↓ 21 · ♥ 1
Params
31M
Weights
≈ 122 MB
Mac memory
8 GB+

mit · updated 2026-06-05

FuseO1-R1-QwQ-SkyT1-Flash-32B-Q8

from FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview
8-bit
Uncategorised · FuseAI ↓ 21 · ♥ 1
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-02-21

Gabliterated-Qwen3-0.6B-float32

from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated-Dev
Text generation · Goekdeniz-Guelmez ↓ 21 · ♥ 1
Params
596M
Weights
≈ 2.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-28

Jedi-7B-1080p-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 21 · ♥ 1
Params
8.3B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-01

Lumimaid-v0.2-70B

from NeverSleep/Lumimaid-v0.2-70B
8-bit
Uncategorised · NeverSleep ↓ 21 · ♥ 1
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

cc-by-nc-4.0 · updated 2024-10-13

SigLIP2-NR-IQA-KonIQ

from google/siglip2-so400m-patch16-512
Image classification · Google · Gemma ↓ 21 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-06-06

UI-TARS-72B-DPO-bf16

mlx-community/UI-TARS-72B-DPO-bf16
bf16
Vision + text ↓ 21 · ♥ 1
Params
73B
Weights
≈ 147 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-03-06

bagel-dpo-1.1b-v0.3-mlx

mlx-community/bagel-dpo-1.1b-v0.3-mlx
Uncategorised ↓ 21 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-01-10

dolphin-2.2-yi-34b-200k-8bit

mlx-community/dolphin-2.2-yi-34b-200k-8bit
8-bit
Uncategorised ↓ 21 · ♥ 1
Params
34B
Weights
≈ 37.0 GB
Mac memory
48 GB+

yi-license · updated 2024-04-07

dolphin-2.9-llama3-8b-1m-8bit

from meta-llama/Meta-Llama-3-8B
8-bit
Uncategorised · Meta · Llama ↓ 21 · ♥ 1
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

other · updated 2024-04-30

mamba-370m-hf-f16

from state-spaces/mamba-370m-hf
Text generation · state-spaces ↓ 21 · ♥ 1
Params
372M
Weights
≈ 743 MB
Mac memory
8 GB+

updated 2024-09-21

sam3-mxfp4

from facebook/sam3
MXFP4
Uncategorised · facebook ↓ 21 · ♥ 1
Params
860M
Weights
≈ 568 MB
Mac memory
8 GB+

updated 2026-03-28

ArrowCanaria-Llama-8B-RL-v0.1-MLX-8bit

from DataPilot/ArrowCanaria-Llama-8B-RL-v0.1
8-bit
Text generation · DataPilot ↓ 21 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.3 · updated 2026-03-27

CapybaraHermes-2.5-Mistral-7B

from teknium/OpenHermes-2.5-Mistral-7B
Uncategorised · teknium ↓ 21 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-04-07

Cydonia-24B-v3.1-bf16

from TheDrummer/Cydonia-24B-v3.1
bf16
Text generation · TheDrummer ↓ 21 · ♥ 0
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+

updated 2025-06-25

Falcon-H1-0.5B-Instruct-bf16

from tiiuae/Falcon-H1-0.5B-Instruct
bf16
Text generation · TII · Falcon ↓ 21 · ♥ 0
Params
521M
Weights
≈ 1.0 GB
Mac memory
8 GB+

falcon-llm-license · updated 2025-09-26

Falcon-H1-Tiny-90M-Base-bf16

from tiiuae/Falcon-H1-Tiny-90M-Base
bf16
Text generation · TII · Falcon ↓ 21 · ♥ 0
Params
91M
Weights
≈ 182 MB
Mac memory
8 GB+

falcon-llm-license · updated 2026-01-28

Falcon-H1-Tiny-90M-Instruct-Curriculum-bf16

from tiiuae/Falcon-H1-Tiny-90M-Instruct-Curriculum
bf16
Text generation · TII · Falcon ↓ 21 · ♥ 0
Params
91M
Weights
≈ 182 MB
Mac memory
8 GB+

falcon-llm-license · updated 2026-01-28

Falcon-H1-Tiny-R-0.6B-pre-GRPO-bf16

from tiiuae/Falcon-H1-Tiny-R-0.6B-pre-GRPO
bf16
Text generation · TII · Falcon ↓ 21 · ♥ 0
Params
622M
Weights
≈ 1.2 GB
Mac memory
8 GB+

falcon-llm-license · updated 2026-01-28

Falcon3-1B-Instruct-1.58bit

from tiiuae/Falcon3-1B-Instruct-1.58bit
58-bit
Text generation · TII · Falcon ↓ 21 · ♥ 0
Params
820M
Weights
≈ 1.4 GB
Mac memory
8 GB+

falcon-llm-license · updated 2025-06-10

Falcon3-1B-Instruct-6bit

from tiiuae/Falcon3-1B-Instruct
6-bit
Text generation · TII · Falcon ↓ 21 · ♥ 0
Params
1.7B
Weights
≈ 1.4 GB
Mac memory
8 GB+

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

GLM-4.5V-abliterated-6bit

mlx-community/GLM-4.5V-abliterated-6bit
6-bit
Uncategorised ↓ 21 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-08-24

Gemma-3-Glitter-12B-8bit

from allura-org/Gemma-3-Glitter-12B
8-bit
Vision + text · allura-org ↓ 21 · ♥ 0
Params
12B
Weights
≈ 12.5 GB
Mac memory
16 GB+

updated 2025-09-29

InternVL3-14B-6bit

from OpenGVLab/InternVL3-1B-Instruct
6-bit
Vision + text · OpenGVLab ↓ 21 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-30

InternVL3-14B-bf16

from OpenGVLab/InternVL3-1B-Instruct
bf16
Vision + text · OpenGVLab ↓ 21 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-30

Jan-v1-4B-6bit

from janhq/Jan-v1-4B
6-bit
Text generation · janhq ↓ 21 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-12

LFM2.5-1.2B-Base-5bit

from LiquidAI/LFM2.5-1.2B-Base
5-bit
Text generation · LiquidAI ↓ 21 · ♥ 0
Params
1.2B
Weights
≈ 805 MB
Mac memory
8 GB+

other · updated 2026-01-06

LFM2.5-1.2B-JP-8bit

from LiquidAI/LFM2.5-1.2B-JP
8-bit
Text generation · LiquidAI ↓ 21 · ♥ 0
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

LLaMA-Pro-8B-Instruct-mlx

mlx-community/LLaMA-Pro-8B-Instruct-mlx
Uncategorised ↓ 21 · ♥ 0
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-01-08

Laguna-XS.2-2bit-M-DQ

from poolside/Laguna-XS.2
2-bit
Text generation · poolside ↓ 21 · ♥ 0
Params
33B
Weights
≈ 10.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-04-29

Lingshu-32B-bf16

mlx-community/Lingshu-32B-bf16
bf16
Vision + text ↓ 21 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-06-12

LongCat-Flash-Thinking-2601-6bit

from meituan-longcat/LongCat-Flash-Thinking-2601
6-bit
Text generation · meituan-longcat ↓ 21 · ♥ 0
Params
561B
Weights
≈ 456 GB
Mac memory
512 GB+

mit · updated 2026-01-18

Nex-N2-mini-5bit

from nex-agi/Nex-N2-mini
5-bit
Text generation · nex-agi ↓ 21 · ♥ 0
Params
35B
Weights
≈ 24.7 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-06-08

Olmo-3-1025-7B-6bit

from allenai/Olmo-3-1025-7B
6-bit
Text generation · Ai2 · OLMo ↓ 21 · ♥ 0
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-21

Olmo-3-1125-32B-6bit

from allenai/Olmo-3-1125-32B
6-bit
Text generation · Ai2 · OLMo ↓ 21 · ♥ 0
Params
32B
Weights
≈ 26.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-11-21

Olmo-3-7B-Think-SFT-bfloat16

from allenai/Olmo-3-7B-Think-SFT
Text generation · Ai2 · OLMo ↓ 21 · ♥ 0
Params
7.3B
Weights
≈ 14.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-11-21

P1-VL-30B-A3B-4bit

from PRIME-RL/P1-VL-30B-A3B
4-bit
Vision + text · PRIME-RL ↓ 21 · ♥ 0
Params
31B
Weights
≈ 18.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-05-18

PE-Core-G14-448

from facebook/PE-Core-G14-448
Uncategorised · facebook ↓ 21 · ♥ 0
Params
2.4B
Weights
≈ 9.7 GB
Mac memory
16 GB+

updated 2025-12-26

Qwen3-VL-2B-Thinking-6bit

mlx-community/Qwen3-VL-2B-Thinking-6bit
6-bit
Vision + text ↓ 21 · ♥ 0
Params
2.1B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

Qwen3-VL-32B-Thinking-6bit

mlx-community/Qwen3-VL-32B-Thinking-6bit
6-bit
Vision + text ↓ 21 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-21

Qwen3.5-0.8B-mixed_2_6

mlx-community/Qwen3.5-0.8B-mixed_2_6
4-bit
Uncategorised ↓ 21 · ♥ 0
Params
209M
Weights
≈ 297 MB
Mac memory
8 GB+

updated 2026-03-02

Qwen3.5-0.8B-mixed_3_6

mlx-community/Qwen3.5-0.8B-mixed_3_6
4-bit
Uncategorised ↓ 21 · ♥ 0
Params
223M
Weights
≈ 305 MB
Mac memory
8 GB+

updated 2026-03-02

Qwen3.5-2B-mixed_2_6

mlx-community/Qwen3.5-2B-mixed_2_6
4-bit
Uncategorised ↓ 21 · ♥ 0
Params
591M
Weights
≈ 894 MB
Mac memory
8 GB+

updated 2026-03-02