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

Alert me about new Apple/MLX models

2,922 builds · page 28 of 49 · clear filters

OLMo-2-1124-7B-Instruct-6bit

from allenai/OLMo-2-1124-7B-Instruct
6-bit
Text generation · Ai2 · OLMo ↓ 48 · ♥ 0
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-11-27

Qwen2.5-7B-Instruct-kowiki-qa-8bit

mlx-community/Qwen2.5-7B-Instruct-kowiki-qa-8bit
8-bit
Text generation ↓ 48 · ♥ 0
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-12-20

SmolLM3-3B-5bit

from HuggingFaceTB/SmolLM3-3B
5-bit
Text generation · Hugging Face ↓ 48 · ♥ 0
Params
3.1B
Weights
≈ 2.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-08

gemma-3-1b-it-abliterated-6bit

from mlabonne/gemma-3-1b-it-abliterated
6-bit
Text generation · mlabonne ↓ 48 · ♥ 0
Params
1.3B
Weights
≈ 1.1 GB
Mac memory
8 GB+

gemma · updated 2025-03-22

gemma-4-12B-it-qat-assistant-nvfp4

from google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
4-bit
Text generation · Google · Gemma ↓ 48 · ♥ 0
Params
423M
Weights
≈ 238 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

gemma-4-E2B-it-qat-assistant-nvfp4

from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
4-bit
Text generation · Google · Gemma ↓ 48 · ♥ 0
Params
78M
Weights
≈ 45 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

gemma2-9b-cpt-sahabatai-v1-instruct-8bit

from GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
8-bit
Text generation · GoToCompany ↓ 48 · ♥ 0
Params
9.2B
Weights
≈ 9.8 GB
Mac memory
16 GB+

gemma · updated 2026-06-04

granite-20b-code-base-4bit

mlx-community/granite-20b-code-base-4bit
4-bit
Text generation ↓ 48 · ♥ 0
Params
20B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-05-14

granite-4.1-30b-8bit

from ibm-granite/granite-4.1-30b
8-bit
Text generation · IBM · Granite ↓ 48 · ♥ 0
Params
29B
Weights
≈ 30.7 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-05-01

llm-jp-3-1.8b-instruct

mlx-community/llm-jp-3-1.8b-instruct
Text generation ↓ 48 · ♥ 0
Params
1.9B
Weights
≈ 3.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-25

llm-jp-3.1-1.8b-instruct4-8bit

from llm-jp/llm-jp-3.1-1.8b-instruct4
8-bit
Text generation · llm-jp ↓ 48 · ♥ 0
Params
1.9B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-16

quantized-gemma-7b

mlx-community/quantized-gemma-7b
Text generation ↓ 48 · ♥ 0
Params
8.5B
Weights
≈ 32.6 GB
Mac memory
48 GB+

gemma-terms-of-use · updated 2024-02-21

Qwen3-30B-A3B-4bit-DWQ-053125

from Qwen/Qwen3-30B-A3B
4-bit DWQ
Text generation · Qwen ↓ 47 · ♥ 7
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-02

LFM2.5-1.2B-Thinking-8bit

from LiquidAI/LFM2.5-1.2B-Thinking
8-bit
Text generation · LiquidAI ↓ 47 · ♥ 3
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

RakutenAI-3.0-MLX-4bit

from Rakuten/RakutenAI-3.0
4-bit
Text generation · Rakuten ↓ 47 · ♥ 2
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+

apache-2.0 · updated 2026-03-31

Saka-14B-4bit

from Sakalti/Saka-14B
4-bit
Text generation · Sakalti ↓ 47 · ♥ 2
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

updated 2025-02-12

granite-4.1-30b-nvfp4

from ibm-granite/granite-4.1-30b
4-bit
Text generation · IBM · Granite ↓ 47 · ♥ 2
Params
29B
Weights
≈ 16.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-30

Hermes-4-405B-4bit

from NousResearch/Hermes-4-405B
4-bit
Text generation · NousResearch ↓ 47 · ♥ 1
Params
406B
Weights
≈ 228 GB
Mac memory
512 GB+

llama3 · updated 2025-08-27

HuatuoGPT-o1-72B-4bit

from FreedomIntelligence/HuatuoGPT-o1-72B
4-bit
Text generation · FreedomIntelligence ↓ 47 · ♥ 1
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-01-06

Laguna-XS.2-8bit

from poolside/Laguna-XS.2
8-bit
Text generation · poolside ↓ 47 · ♥ 1
Params
33B
Weights
≈ 35.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-28

Llama-3-8B-Instruct-262k-unquantized

mlx-community/Llama-3-8B-Instruct-262k-unquantized
Text generation ↓ 47 · ♥ 1
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

updated 2024-04-26

LongWriter-llama3.1-8b-8bit

from zai-org/LongWriter-llama3.1-8b
8-bit
Text generation · zai-org ↓ 47 · ♥ 1
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.1 · updated 2025-09-29

Youtu-LLM-2B

from tencent/Youtu-LLM-2B
Text generation · tencent ↓ 47 · ♥ 1
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

tencent-youtu · updated 2026-01-01

granite-34b-code-base-8bit

mlx-community/granite-34b-code-base-8bit
8-bit
Text generation ↓ 47 · ♥ 1
Params
34B
Weights
≈ 35.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2024-05-14

II-Medical-8B-4bit

from Intelligent-Internet/II-Medical-8B
4-bit
Text generation · Intelligent-Internet ↓ 47 · ♥ 0
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

updated 2025-06-04

Josiefied-Qwen3-0.6B-abliterated-v1-6bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v1
6-bit
Text generation · Goekdeniz-Guelmez ↓ 47 · ♥ 0
Params
596M
Weights
≈ 484 MB
Mac memory
8 GB+

updated 2025-04-29

Llama-2-7b-Ukrainian

from tartuNLP/Llama-2-7b-Ukrainian
Text generation · tartuNLP ↓ 47 · ♥ 0
Params
6.7B
Weights
≈ 13.5 GB
Mac memory
24 GB+

llama2 · updated 2025-12-17

Pearl-3x7B

from louisbrulenaudet/Pearl-3x7B
Text generation · louisbrulenaudet ↓ 47 · ♥ 0
Params
19B
Weights
≈ 73.8 GB
Mac memory
96 GB+

apache-2.0 · updated 2024-08-06

Qwen1.5-4B-Chat-4bit

mlx-community/Qwen1.5-4B-Chat-4bit
4-bit
Text generation ↓ 47 · ♥ 0
Params
4.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

tongyi-qianwen-research · updated 2024-03-07

Qwen3-4B-Instruct-2507-5.0bpw-dynamic

from Qwen/Qwen3-4B-Instruct-2507
4-bit
Text generation · Qwen ↓ 47 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-11

gemma-2-27b-4bit

mlx-community/gemma-2-27b-4bit
4-bit
Text generation ↓ 47 · ♥ 0
Params
27B
Weights
≈ 15.3 GB
Mac memory
24 GB+

gemma · updated 2024-06-27

gemma-3-1b-pt-bf16

from google/gemma-3-1b-pt
bf16
Text generation · Google · Gemma ↓ 47 · ♥ 0
Params
1.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+

gemma · updated 2025-03-12

openchat-3.5-1210-7b-mlx

from mistralai/Mistral-7B-v0.1
Text generation · Mistral ↓ 47 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-01-08

rnj-1-instruct-4bit

from EssentialAI/rnj-1-instruct
4-bit
Text generation · EssentialAI ↓ 47 · ♥ 0
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-20

Magistral-Small-2506-bf16

from mistralai/Magistral-Small-2506
bf16
Text generation · Mistral ↓ 46 · ♥ 10
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-06-10

phi-2-4bit

mlx-community/phi-2-4bit
4-bit
Text generation ↓ 46 · ♥ 5
Params
—
Weights
—
Mac memory
—

microsoft-research-license · updated 2023-12-22

CodeLlama-34b-Instruct-hf-6bit-mlx

from codellama/CodeLlama-34b-Instruct-hf
6-bit
Text generation · codellama ↓ 46 · ♥ 1
Params
34B
Weights
≈ 27.4 GB
Mac memory
48 GB+

llama2 · updated 2025-04-27

Deductive-Reasoning-Qwen-32B-MLX-6bit

from OpenPipe/Deductive-Reasoning-Qwen-32B
6-bit
Text generation · OpenPipe ↓ 46 · ♥ 1
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+

mit · updated 2025-03-11

EXAONE-Deep-2.4B-4bit

from LGAI-EXAONE/EXAONE-Deep-2.4B
4-bit
Text generation · LGAI-EXAONE ↓ 46 · ♥ 1
Params
2.4B
Weights
≈ 1.4 GB
Mac memory
8 GB+

exaone · updated 2025-03-18

Josiefied-Olmo-3-7B-Instruct-abliterated-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
4-bit
Text generation · Goekdeniz-Guelmez ↓ 46 · ♥ 1
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+

updated 2025-11-25

Ling-2.6-flash-mlx-6bit

from inclusionAI/Ling-2.6-flash
6-bit
Text generation · inclusionAI ↓ 46 · ♥ 1
Params
104B
Weights
≈ 84.7 GB
Mac memory
128 GB+

mit · updated 2026-04-29

Mellum-4b-base-8bit

from JetBrains/Mellum-4b-base
8-bit
Text generation · JetBrains ↓ 46 · ♥ 1
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-28

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr9e-8

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 46 · ♥ 1
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

RakutenAI-2.0-mini-MLX-8bit

from Rakuten/RakutenAI-2.0-mini
8-bit
Text generation · Rakuten ↓ 46 · ♥ 1
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-20

glm-4-9b-chat-1m-bf16

from zai-org/glm-4-9b-chat-1m-hf
bf16
Text generation · zai-org ↓ 46 · ♥ 1
Params
9.5B
Weights
≈ 19.0 GB
Mac memory
24 GB+

glm-4 · updated 2025-09-14

helium-1-preview-2b-4bit

from kyutai/helium-1-preview-2b
4-bit
Text generation · kyutai ↓ 46 · ♥ 1
Params
2.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+

cc-by-4.0 · updated 2025-01-18

CodeLlama-34b-Instruct-hf-4bit-mlx

from codellama/CodeLlama-34b-Instruct-hf
4-bit
Text generation · codellama ↓ 46 · ♥ 0
Params
34B
Weights
≈ 19.0 GB
Mac memory
24 GB+

llama2 · updated 2025-04-28

Gemma-SEA-LION-v4.5-E2B-IT-4bits

from aisingapore/Gemma-SEA-LION-v4.5-E2B-IT
4-bit
Text generation · aisingapore ↓ 46 · ♥ 0
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+

mit · updated 2026-06-23

Josiefied-Hermes-3-Llama-3.2-3B-v1-6bit

from Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
6-bit
Text generation · Goekdeniz-Guelmez ↓ 46 · ♥ 0
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+

updated 2025-10-28

LFM2-8B-A1B-5bit

from LiquidAI/LFM2-8B-A1B
5-bit
Text generation · LiquidAI ↓ 46 · ♥ 0
Params
8.3B
Weights
≈ 5.7 GB
Mac memory
16 GB+

lfm1.0 · updated 2025-10-08

Llama-3.1-Swallow-8B-Instruct-v0.5

from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5
Text generation · tokyotech-llm ↓ 46 · ♥ 0
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3.3 · updated 2025-06-25

Meta-Llama-3-70B-Instruct-mlx-unquantized

mlx-community/Meta-Llama-3-70B-Instruct-mlx-unquantized
Text generation ↓ 46 · ♥ 0
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+

llama3 · updated 2024-04-30

OLMoE-1B-7B-0125-Instruct

from allenai/OLMoE-1B-7B-0125-Instruct
Text generation · Ai2 · OLMo ↓ 46 · ♥ 0
Params
6.9B
Weights
≈ 13.8 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-04

Qwen3-4B-Instruct-2507-gabliterated-bf16

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
bf16
Text generation · Goekdeniz-Guelmez ↓ 46 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2026-01-06

TinyR1-32B-Preview-8bit

from qihoo360/TinyR1-32B-Preview
8-bit
Text generation · qihoo360 ↓ 46 · ♥ 0
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-02-26

gemma-3-4b-it-5bit

from google/gemma-3-4b-it
5-bit
Text generation · Google · Gemma ↓ 46 · ♥ 0
Params
3.9B
Weights
≈ 2.7 GB
Mac memory
8 GB+

gemma · updated 2025-10-09

gemma-3n-E4B-it-text-4bit-dwq

from google/gemma-3n-E4B-it
4-bit DWQ
Text generation · Google · Gemma ↓ 46 · ♥ 0
Params
6.9B
Weights
≈ 9.6 GB
Mac memory
16 GB+

gemma · updated 2025-07-27

granite-4.0-1b-8bit

from ibm-granite/granite-4.0-1b
8-bit
Text generation · IBM · Granite ↓ 46 · ♥ 0
Params
1.6B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

llm-jp-3.1-13b-instruct4

from llm-jp/llm-jp-3.1-13b-instruct4
Text generation · llm-jp ↓ 46 · ♥ 0
Params
14B
Weights
≈ 27.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-06-16