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

2,922 builds · page 14 of 49 · clear filters

quantized-gemma-2b-it

mlx-community/quantized-gemma-2b-it
Text generation ↓ 134 · ♥ 10
Params
2.5B
Weights
≈ 9.0 GB
Mac memory
16 GB+

gemma-terms-of-use · updated 2024-02-22

DeepSeek-R1-0528-Qwen3-8B-8bit

from deepseek-ai/deepseek-r1-0528-Qwen3-8B
8-bit
Text generation · DeepSeek ↓ 134 · ♥ 3
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+

mit · updated 2025-05-29

Llama-3.1-Swallow-8B-Instruct-v0.5-4bit

from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5
4-bit
Text generation · tokyotech-llm ↓ 134 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3.3 · updated 2025-06-25

CodeLlama-70b-Python-hf-4bit-MLX

mlx-community/CodeLlama-70b-Python-hf-4bit-MLX
4-bit
Text generation ↓ 133 · ♥ 11
Params
—
Weights
—
Mac memory
—

llama2 · updated 2024-01-30

functiongemma-270m-it-bf16

from google/functiongemma-270m-it
bf16
Text generation · Google · Gemma ↓ 133 · ♥ 7
Params
268M
Weights
≈ 536 MB
Mac memory
8 GB+

gemma · updated 2025-12-18

Huihui-gemma-3n-E4B-it-abliterated-lm-8bit

from huihui-ai/Huihui-gemma-3n-E4B-it-abliterated
8-bit
Text generation · huihui-ai ↓ 133 · ♥ 1
Params
6.9B
Weights
≈ 7.3 GB
Mac memory
16 GB+

gemma · updated 2025-09-25

NVIDIA-Nemotron-3-Nano-4B-6bit

from nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
6-bit
Text generation · NVIDIA ↓ 133 · ♥ 1
Params
4.0B
Weights
≈ 3.2 GB
Mac memory
8 GB+

nvidia-nemotron-open-model-license · updated 2026-03-20

phi-4-3bit

from microsoft/phi-4
3-bit
Text generation · Microsoft · Phi ↓ 133 · ♥ 0
Params
15B
Weights
≈ 6.4 GB
Mac memory
16 GB+

mit · updated 2025-01-12

QwQ-32B-4bit

from Qwen/QwQ-32B
4-bit
Text generation · Qwen ↓ 132 · ♥ 38
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-05

deepseek-ai-DeepSeek-V4-Flash-6bit

from deepseek-ai/DeepSeek-V4-Flash
6-bit
Text generation · DeepSeek ↓ 132 · ♥ 2
Params
284B
Weights
≈ 231 GB
Mac memory
512 GB+

mit · updated 2026-04-24

Seed-Coder-8B-Instruct-6bit

from ByteDance-Seed/Seed-Coder-8B-Instruct
6-bit
Text generation · ByteDance-Seed ↓ 132 · ♥ 1
Params
8.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+

mit · updated 2025-05-20

SmolLM3-3B-8bit

from HuggingFaceTB/SmolLM3-3B
8-bit
Text generation · Hugging Face ↓ 131 · ♥ 9
Params
3.1B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-08

Llama-3.1-Nemotron-70B-Instruct-HF

from nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Text generation · NVIDIA ↓ 131 · ♥ 3
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+

llama3.1 · updated 2024-10-16

LFM2-700M-4bit

from LiquidAI/LFM2-700M
4-bit
Text generation · LiquidAI ↓ 131 · ♥ 1
Params
742M
Weights
≈ 418 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-07-11

Hermes-4-70B-4bit

from NousResearch/Hermes-4-70B
4-bit
Text generation · NousResearch ↓ 131 · ♥ 0
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

llama3 · updated 2025-08-26

DeepSeek-V3.2_bf16

from deepseek-ai/DeepSeek-V3.2
bf16
Text generation · DeepSeek ↓ 130 · ♥ 1
Params
672B
Weights
≈ 1344 GB
Mac memory
> 512 GB

mit · updated 2025-12-03

DeepSeek-V4-Flash-MTP-bf16

from deepseek-ai/DeepSeek-V4-Flash
bf16
Text generation · DeepSeek ↓ 130 · ♥ 1
Params
6.6B
Weights
≈ 26.4 GB
Mac memory
32 GB+

mit · updated 2026-06-01

gemma-4-E2B-it-qat-assistant-mxfp4

from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
MXFP4
Text generation · Google · Gemma ↓ 130 · ♥ 1
Params
78M
Weights
≈ 45 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

c4ai-command-r7b-12-2024-4bit

from CohereLabs/c4ai-command-r7b-12-2024
4-bit
Text generation · Cohere ↓ 130 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2024-12-14

DeepSeek-V4-Flash-2bit-M-DQ

from deepseek-ai/DeepSeek-V4-Flash
2-bit
Text generation · DeepSeek ↓ 129 · ♥ 3
Params
284B
Weights
≈ 89.1 GB
Mac memory
128 GB+

mit · updated 2026-04-28

VibeThinker-3B-OptiQ-4bit

from WeiboAI/VibeThinker-3B
4-bit
Text generation · WeiboAI ↓ 129 · ♥ 3
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

mit · updated 2026-09-14

Phi-4-reasoning-plus-8bit

from microsoft/Phi-4-reasoning-plus
8-bit
Text generation · Microsoft · Phi ↓ 129 · ♥ 1
Params
15B
Weights
≈ 15.6 GB
Mac memory
24 GB+

mit · updated 2025-05-01

MiMo-7B-SFT-4bit

from XiaomiMiMo/MiMo-7B-SFT
4-bit
Text generation · XiaomiMiMo ↓ 129 · ♥ 0
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

mit · updated 2025-05-02

S1-mini-MLX-8bit

from superwhisper/s1-mini
8-bit
Text generation · superwhisper ↓ 129 · ♥ 0
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+

s1-mini-license · updated 2026-08-20

internlm2_5-7b-chat-8bit

mlx-community/internlm2_5-7b-chat-8bit
8-bit
Text generation ↓ 128 · ♥ 3
Params
7.7B
Weights
≈ 8.2 GB
Mac memory
16 GB+

other · updated 2024-07-04

Qwen3.5-9B-MTP-5bit

from Qwen/Qwen3.5-9B
5-bit
Text generation · Qwen ↓ 128 · ♥ 1
Params
243M
Weights
≈ 167 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

ELYZA-Thinking-1.0-Qwen-32B-8bit

from elyza/ELYZA-Thinking-1.0-Qwen-32B
8-bit
Text generation · elyza ↓ 127 · ♥ 1
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-05-01

BigBang-v1-MLX-oQ4e

from endless-frontier/BigBang-v1
4-bit
Text generation · endless-frontier ↓ 127 · ♥ 0
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-09-11

INTELLECT-1-Instruct-4bit

from PrimeIntellect/INTELLECT-1-Instruct
4-bit
Text generation · PrimeIntellect ↓ 127 · ♥ 0
Params
10B
Weights
≈ 5.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-11-30

Unsloth-Phi-4-4bit

from unsloth/phi-4
4-bit
Text generation · unsloth ↓ 126 · ♥ 7
Params
15B
Weights
≈ 8.2 GB
Mac memory
16 GB+

mit · updated 2025-01-13

Devstral-2-123B-Instruct-2512-5bit

from mistralai/Devstral-2-123B-Instruct-2512
5-bit
Text generation · Mistral ↓ 126 · ♥ 0
Params
125B
Weights
≈ 86.0 GB
Mac memory
128 GB+

other · updated 2025-12-10

Qwen2.5-7B-Instruct-1M-8bit

from Qwen/Qwen2.5-7B-Instruct-1M
8-bit
Text generation · Qwen ↓ 124 · ♥ 4
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-01-26

gemma-2-2b-it-8bit

mlx-community/gemma-2-2b-it-8bit
8-bit
Text generation ↓ 124 · ♥ 3
Params
2.6B
Weights
≈ 2.8 GB
Mac memory
8 GB+

gemma · updated 2024-11-06

LFM2.5-2.6B-6bit

from LiquidAI/LFM2.5-2.6B
6-bit
Text generation · LiquidAI ↓ 124 · ♥ 1
Params
2.7B
Weights
≈ 2.2 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

AceReason-Nemotron-7B-4bit

from nvidia/AceReason-Nemotron-7B
4-bit
Text generation · NVIDIA ↓ 124 · ♥ 0
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

nvidia-open-model-license · updated 2025-05-26

INTELLECT-3-4bit

from PrimeIntellect/INTELLECT-3
4-bit
Text generation · PrimeIntellect ↓ 123 · ♥ 3
Params
107B
Weights
≈ 60.1 GB
Mac memory
96 GB+

mit · updated 2025-11-27

Llama-3.1-405B-Instruct-8bit

from meta-llama/Llama-3.1-405B-Instruct
8-bit
Text generation · Meta · Llama ↓ 123 · ♥ 2
Params
406B
Weights
≈ 431 GB
Mac memory
512 GB+

llama3.1 · updated 2024-11-06

OpenCodeInterpreter-DS-6.7B-4bit

mlx-community/OpenCodeInterpreter-DS-6.7B-4bit
4-bit
Text generation ↓ 123 · ♥ 1
Params
6.7B
Weights
≈ 4.0 GB
Mac memory
8 GB+

updated 2024-02-24

Llama-3.1-Swallow-8B-Instruct-v0.3-4bit

from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3
4-bit
Text generation · tokyotech-llm ↓ 123 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3.1 · updated 2024-12-23

MiniMax-M2.7-6bit

from MiniMaxAI/MiniMax-M2.7
6-bit
Text generation · MiniMaxAI ↓ 122 · ♥ 1
Params
229B
Weights
≈ 186 GB
Mac memory
256 GB+

modified-mit · updated 2026-04-12

Falcon3-3B-Instruct-4bit

from tiiuae/Falcon3-3B-Instruct
4-bit
Text generation · TII · Falcon ↓ 122 · ♥ 0
Params
3.2B
Weights
≈ 1.8 GB
Mac memory
8 GB+

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

MiniMax-M2.7-3bit

from MiniMaxAI/MiniMax-M2.7
3-bit
Text generation · MiniMaxAI ↓ 121 · ♥ 5
Params
229B
Weights
≈ 100 GB
Mac memory
128 GB+

modified-mit · updated 2026-04-12

Qwen2.5-Coder-1.5B-Instruct-Q6

from Qwen/Qwen2.5-Coder-1.5B-Instruct
6-bit
Text generation · Qwen ↓ 121 · ♥ 1
Params
1.5B
Weights
≈ 1.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-18

llm-jp-4-32b-a3b-thinking-8bit

from llm-jp/llm-jp-4-32b-a3b-thinking
8-bit
Text generation · llm-jp ↓ 121 · ♥ 1
Params
32B
Weights
≈ 34.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-12

K2-Horizon-3.7B-bf16

from IFM/K2-Horizon-3.7B
bf16
Text generation · IFM ↓ 121 · ♥ 0
Params
5.1B
Weights
≈ 10.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-30

Qwen3-14B-3bit

from Qwen/Qwen3-14B
3-bit
Text generation · Qwen ↓ 121 · ♥ 0
Params
15B
Weights
≈ 6.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-04-28

llm-jp-4-32b-a3b-thinking-4bit

from llm-jp/llm-jp-4-32b-a3b-thinking
4-bit
Text generation · llm-jp ↓ 121 · ♥ 0
Params
32B
Weights
≈ 18.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-12

gemma-2-9b-it-fp16

mlx-community/gemma-2-9b-it-fp16
fp16
Text generation ↓ 120 · ♥ 2
Params
9.2B
Weights
≈ 18.5 GB
Mac memory
24 GB+

gemma · updated 2024-11-06

Lumimaid-Magnum-12B

from Undi95/Lumimaid-Magnum-12B
8-bit
Text generation · Undi95 ↓ 120 · ♥ 0
Params
12B
Weights
≈ 13.0 GB
Mac memory
24 GB+

updated 2024-10-09

OpenCodeInterpreter-SC2-7B-4bit

mlx-community/OpenCodeInterpreter-SC2-7B-4bit
4-bit
Text generation ↓ 120 · ♥ 0
Params
7.4B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-03-03

Solar-Open-100B-8bit

from upstage/Solar-Open-100B
8-bit
Text generation · upstage ↓ 120 · ♥ 0
Params
103B
Weights
≈ 109 GB
Mac memory
128 GB+

solar-apache-2.0 · updated 2026-01-06

GLM-5

from zai-org/GLM-5
Text generation · zai-org ↓ 119 · ♥ 4
Params
744B
Weights
≈ 1488 GB
Mac memory
> 512 GB

mit · updated 2026-02-12

VulnLLM-R-7B-8bit

from Virtue-AI-HUB/VulnLLM-R-7B
8-bit
Text generation · Virtue-AI-HUB ↓ 119 · ♥ 4
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-01-02

Kimi-Linear-48B-A3B-Instruct-8bit

from moonshotai/Kimi-Linear-48B-A3B-Instruct
8-bit
Text generation · Moonshot · Kimi ↓ 119 · ♥ 1
Params
49B
Weights
≈ 52.2 GB
Mac memory
64 GB+

mit · updated 2026-01-22

Meta-Llama-3.1-8B-Instruct-abliterated

from mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
Text generation · mlabonne ↓ 119 · ♥ 1
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3.1 · updated 2024-09-28

VibeThinker-3B-4bit

from WeiboAI/VibeThinker-3B
4-bit
Text generation · WeiboAI ↓ 119 · ♥ 1
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

mit · updated 2026-06-16

Qwen2.5-Coder-0.5B-Instruct-bf16

from Qwen/Qwen2.5-Coder-0.5B-Instruct
bf16
Text generation · Qwen ↓ 119 · ♥ 0
Params
494M
Weights
≈ 988 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-11