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 73 of 98

Qwen3-30B-4bit-DWQ-053125

from Qwen/Qwen3-32B
4-bit DWQ
Text generation · Qwen ↓ 30 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-02

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr2e-7

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 30 · ♥ 0
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr3e-8

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 30 · ♥ 0
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-VL-8B-Thinking-3bit

mlx-community/Qwen3-VL-8B-Thinking-3bit
3-bit
Vision + text ↓ 30 · ♥ 0
Params
8.8B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

Qwen3-VL-8B-Thinking-5bit

mlx-community/Qwen3-VL-8B-Thinking-5bit
5-bit
Vision + text ↓ 30 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

Qwen3-VL-Embedding-2B-nvfp4

from Qwen/Qwen3-VL-2B-Instruct
Embeddings · Qwen ↓ 30 · ♥ 0
Params
2.1B
Weights
≈ 7.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-13

Qwen3.5-2B-mixed_4_6

mlx-community/Qwen3.5-2B-mixed_4_6
4-bit
Uncategorised ↓ 30 · ♥ 0
Params
667M
Weights
≈ 937 MB
Mac memory
8 GB+

updated 2026-03-02

RakutenAI-7B-instruct-MLX-4bit

from Rakuten/RakutenAI-7B-instruct
4-bit
Text generation · Rakuten ↓ 30 · ♥ 0
Params
7.4B
Weights
≈ 4.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-20

Ring-flash-linear-2.0-4bit

from inclusionAI/Ring-flash-linear-2.0
4-bit
Text generation · inclusionAI ↓ 30 · ♥ 0
Params
104B
Weights
≈ 58.6 GB
Mac memory
96 GB+

mit · updated 2025-10-17

Seed-Coder-8B-Reasoning-bf16-mlx-fp16

from ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16
bf16
Text generation · ByteDance-Seed ↓ 30 · ♥ 0
Params
8.3B
Weights
≈ 16.5 GB
Mac memory
24 GB+

mit · updated 2025-07-18

SmolLM-360M-fp16

mlx-community/SmolLM-360M-fp16
fp16
Text generation ↓ 30 · ♥ 0
Params
362M
Weights
≈ 724 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-07-16

SmolLM3-3B-gabliterated-bf16

from HuggingFaceTB/SmolLM3-3B
bf16
Text generation · Hugging Face ↓ 30 · ♥ 0
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-07-10

Tess-4-27B-8bit

from migtissera/Tess-4-27B
8-bit
Vision + text · migtissera ↓ 30 · ♥ 0
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-10

answerdotai-ModernBERT-Large-Instruct-4bit

mlx-community/answerdotai-ModernBERT-Large-Instruct-4bit
4-bit
Fill mask ↓ 30 · ♥ 0
Params
447M
Weights
≈ 252 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-02

dolphin-2.9.2-qwen2-72b-2bit

from Qwen/Qwen2-72B
2-bit
Uncategorised · Qwen ↓ 30 · ♥ 0
Params
6.8B
Weights
≈ 6.0 GB
Mac memory
16 GB+

tongyi-qianwen · updated 2024-06-07

gemma-2-9b-it-SimPO-mixed-3-6-bit

from princeton-nlp/gemma-2-9b-it-SimPO
6-bit
Text generation · princeton-nlp ↓ 30 · ♥ 0
Params
9.2B
Weights
≈ 7.5 GB
Mac memory
16 GB+

mit · updated 2025-07-22

gemma-4-E4B-it-qat-5bit

mlx-community/gemma-4-E4B-it-qat-5bit
5-bit
Vision + text ↓ 30 · ♥ 0
Params
7.9B
Weights
≈ 6.1 GB
Mac memory
16 GB+

updated 2026-06-05

granite-4.0-1b-base-8bit

from ibm-granite/granite-4.0-1b-base
8-bit
Text generation · IBM · Granite ↓ 30 · ♥ 0
Params
1.6B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

granite-4.1-8b-5bit

from ibm-granite/granite-4.1-8b
5-bit
Text generation · IBM · Granite ↓ 30 · ♥ 0
Params
8.4B
Weights
≈ 5.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-05-03

h2o-danube-1.8b-chat-4bit-mlx

mlx-community/h2o-danube-1.8b-chat-4bit-mlx
4-bit
Text generation ↓ 30 · ♥ 0
Params
1.8B
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-01-31

karakuri-lm-8x7b-instruct-v0.1-4bit

from karakuri-ai/karakuri-lm-8x7b-instruct-v0.1
4-bit
Text generation · karakuri-ai ↓ 30 · ♥ 0
Params
47B
Weights
≈ 26.3 GB
Mac memory
32 GB+

apache-2.0 · updated 2024-10-11

lille-130m-instruct-6bit

from mlx-community/lille-130m-instruct-fp16
6-bit
Text generation ↓ 30 · ♥ 0
Params
127M
Weights
≈ 103 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-09-05

llava-interleave-qwen-0.5b-4bit

mlx-community/llava-interleave-qwen-0.5b-4bit
4-bit
Vision + text ↓ 30 · ♥ 0
Params
864M
Weights
≈ 1.1 GB
Mac memory
8 GB+

tongyi-qianwen-research · updated 2025-03-27

llava-interleave-qwen-7b-4bit

mlx-community/llava-interleave-qwen-7b-4bit
4-bit
Vision + text ↓ 30 · ♥ 0
Params
8.1B
Weights
≈ 5.2 GB
Mac memory
8 GB+

tongyi-qianwen-research · updated 2025-03-27

llava-interleave-qwen-7b-6bit

mlx-community/llava-interleave-qwen-7b-6bit
6-bit
Vision + text ↓ 30 · ♥ 0
Params
—
Weights
—
Mac memory
—

tongyi-qianwen-research · updated 2025-03-27

mallam-5b-20k-instructions-v2-mxfp4

from mesolitica/mallam-5b-20k-instructions-v2
MXFP4
Text generation · mesolitica ↓ 30 · ♥ 0
Params
5.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

updated 2026-06-04

paligemma2-3b-mix-448-4bit

mlx-community/paligemma2-3b-mix-448-4bit
4-bit
Vision + text ↓ 30 · ♥ 0
Params
3.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

gemma · updated 2025-02-19

whisper-base-asr-8bit

mlx-community/whisper-base-asr-8bit
8-bit
Speech recognition ↓ 30 · ♥ 0
Params
72M
Weights
≈ 77 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-15

whisper-tiny-8bit

from openai/whisper-tiny
8-bit
Speech recognition · OpenAI · gpt-oss ↓ 30 · ♥ 0
Params
37M
Weights
≈ 40 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

SeaLLM-7B-v2-4bit-mlx

mlx-community/SeaLLM-7B-v2-4bit-mlx
4-bit
Uncategorised ↓ 29 · ♥ 3
Params
7.4B
Weights
≈ 4.4 GB
Mac memory
8 GB+

seallms · updated 2024-02-03

Llama-3-70B-Instruct-Gradient-262k-8bit

mlx-community/Llama-3-70B-Instruct-Gradient-262k-8bit
8-bit
Text generation ↓ 29 · ♥ 2
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3 · updated 2024-05-04

openchat-3.6-8b-20240522-8bit

from meta-llama/Meta-Llama-3-8B
8-bit
Text generation · Meta · Llama ↓ 29 · ♥ 2
Params
2.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+

llama3 · updated 2024-05-24

paligemma2-10b-mix-448-bf16

mlx-community/paligemma2-10b-mix-448-bf16
bf16
Vision + text ↓ 29 · ♥ 2
Params
9.7B
Weights
≈ 19.3 GB
Mac memory
24 GB+

gemma · updated 2025-02-19

INTELLECT-3-5bit

from PrimeIntellect/INTELLECT-3
5-bit
Text generation · PrimeIntellect ↓ 29 · ♥ 1
Params
107B
Weights
≈ 73.5 GB
Mac memory
96 GB+

mit · updated 2025-11-27

Jan-v2-VL-high-4bit-mlx

from janhq/Jan-v2-VL-high
4-bit
Uncategorised · janhq ↓ 29 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-11-15

Josiefied-LFM2.5-1.2B-Instruct-abliterated-6bit

from Goekdeniz-Guelmez/Josiefied-LFM2.5-1.2B-Instruct-abliterated
6-bit
Text generation · Goekdeniz-Guelmez ↓ 29 · ♥ 1
Params
1.2B
Weights
≈ 951 MB
Mac memory
8 GB+

updated 2026-01-26

LFM2-1.2B-5bit

from LiquidAI/LFM2-1.2B
5-bit
Text generation · LiquidAI ↓ 29 · ♥ 1
Params
1.2B
Weights
≈ 805 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-07-12

LFM2.5-VL-1.6B-bf16

from LiquidAI/LFM2.5-1.2B-Base
bf16
Vision + text · LiquidAI ↓ 29 · ♥ 1
Params
1.6B
Weights
≈ 3.2 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

Luni_StarDust-12b-v2

from Luni/StarDust-12b-v2
8-bit
Text generation · Luni ↓ 29 · ♥ 1
Params
12B
Weights
≈ 13.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-10-12

MiniMax-M2.5-5bit

from MiniMaxAI/MiniMax-M2.5
5-bit
Text generation · MiniMaxAI ↓ 29 · ♥ 1
Params
229B
Weights
≈ 157 GB
Mac memory
192 GB+

modified-mit · updated 2026-02-13

Pleias-RAG-350M-6-bit

from PleIAs/Pleias-RAG-350M
6-bit
Text generation · PleIAs ↓ 29 · ♥ 1
Params
353M
Weights
≈ 287 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-24

Qwen2-VL-7B-bf16

mlx-community/Qwen2-VL-7B-bf16
bf16
Vision + text ↓ 29 · ♥ 1
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-24

SERA-32B-4bit

from allenai/SERA-32B
4-bit
Text generation · Ai2 · OLMo ↓ 29 · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-01-27

Step-3.5-Flash-bf16

from stepfun-ai/Step-3.5-Flash
bf16
Text generation · stepfun-ai ↓ 29 · ♥ 1
Params
197B
Weights
≈ 394 GB
Mac memory
512 GB+

apache-2.0 · updated 2026-02-14

c4ai-command-a-03-2025-6bit

from CohereLabs/c4ai-command-a-03-2025
6-bit
Text generation · Cohere ↓ 29 · ♥ 1
Params
111B
Weights
≈ 90.2 GB
Mac memory
128 GB+

cc-by-nc-4.0 · updated 2025-03-18

granite-4.0-1b-base-5bit

from ibm-granite/granite-4.0-1b-base
5-bit
Text generation · IBM · Granite ↓ 29 · ♥ 1
Params
1.6B
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

miscii-14b-0218-4bit

from sthenno-com/miscii-14b-0218
4-bit
Text generation · sthenno-com ↓ 29 · ♥ 1
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-10

sam3-5bit

from facebook/sam3
5-bit
Uncategorised · facebook ↓ 29 · ♥ 1
Params
860M
Weights
≈ 672 MB
Mac memory
8 GB+

updated 2026-03-28

3b-hi-ft-research_release-6bit

from canopylabs/orpheus-3b-0.1-pretrained
6-bit
Text to speech · canopylabs ↓ 29 · ♥ 0
Params
3.3B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-09

ArrowCanaria-Llama-8B-RL-v0.1-MLX-4bit

from DataPilot/ArrowCanaria-Llama-8B-RL-v0.1
4-bit
Text generation · DataPilot ↓ 29 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3.3 · updated 2026-03-27

Cydonia-24B-v3.1-6bit

from TheDrummer/Cydonia-24B-v3.1
6-bit
Text generation · TheDrummer ↓ 29 · ♥ 0
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+

updated 2025-06-25

DeepHermes-3-Llama-3-3B-Preview-MLX

from NousResearch/DeepHermes-3-Llama-3-3B-Preview
Text generation · NousResearch ↓ 29 · ♥ 0
Params
3.2B
Weights
≈ 6.4 GB
Mac memory
16 GB+

llama3 · updated 2025-07-31

DeepHermes-3-Llama-3-8B-Preview-8bit

from NousResearch/DeepHermes-3-Llama-3-8B-Preview
8-bit
Text generation · NousResearch ↓ 29 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3 · updated 2025-03-14

DeepHermes-3-Llama-3-8B-Preview-bf16

from NousResearch/DeepHermes-3-Llama-3-8B-Preview
bf16
Text generation · NousResearch ↓ 29 · ♥ 0
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3 · updated 2025-03-14

Dobby-Mini-Unhinged-Plus-Llama-3.1-8B-bf16

from SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B
bf16
Text generation · SentientAGI ↓ 29 · ♥ 0
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3.1 · updated 2025-06-11

EXAONE-3.5-2.4B-Instruct-bf16

mlx-community/EXAONE-3.5-2.4B-Instruct-bf16
bf16
Uncategorised ↓ 29 · ♥ 0
Params
2.4B
Weights
≈ 4.8 GB
Mac memory
8 GB+

updated 2024-12-09

EXAONE-3.5-7.8B-Instruct-8bit

mlx-community/EXAONE-3.5-7.8B-Instruct-8bit
8-bit
Uncategorised ↓ 29 · ♥ 0
Params
2.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+

updated 2024-12-09

Falcon-H1-1.5B-Instruct-6bit

from tiiuae/Falcon-H1-1.5B-Instruct
6-bit
Text generation · TII · Falcon ↓ 29 · ♥ 0
Params
1.6B
Weights
≈ 1.3 GB
Mac memory
8 GB+

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