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 10 of 49 · clear filters

gemma-4-e4b-it-4bit-MAD

mlx-community/gemma-4-e4b-it-4bit-MAD
4-bit
Text generation ↓ 210 · ♥ 0
Params
7.5B
Weights
≈ 4.2 GB
Mac memory
8 GB+

updated 2026-05-19

Meta-Llama-3-70B-Instruct-8bit

mlx-community/Meta-Llama-3-70B-Instruct-8bit
8-bit
Text generation ↓ 209 · ♥ 6
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3 · updated 2024-04-19

Nemotron-Cascade-2-30B-A3B-6bit

from nvidia/Nemotron-Cascade-2-30B-A3B
6-bit
Text generation · NVIDIA ↓ 209 · ♥ 5
Params
32B
Weights
≈ 25.7 GB
Mac memory
32 GB+

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

Devstral-Small-2505-4bit-DWQ

from mlx-community/Devstral-Small-2505-bf16
4-bit DWQ
Text generation ↓ 209 · ♥ 4
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-05-22

Qwen3.6-27B-MTP-4bit

from Qwen/Qwen3.6-27B
4-bit
Text generation · Qwen ↓ 208 · ♥ 13
Params
425M
Weights
≈ 239 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

Devstral-Small-2507-4bit

from mlx-community/Devstral-Samll-2507-bf16
4-bit
Text generation ↓ 208 · ♥ 1
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-11

Kimi-Dev-72B-4bit

from moonshotai/Kimi-Dev-72B
4-bit
Text generation · Moonshot · Kimi ↓ 207 · ♥ 1
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

mit · updated 2025-07-11

granite-3.3-8b-instruct-4bit

from ibm-granite/granite-3.3-8b-instruct
4-bit
Text generation · IBM · Granite ↓ 207 · ♥ 1
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-16

LFM2.5-1.2B-Instruct-OptiQ-4bit

from LiquidAI/LFM2.5-1.2B-Instruct
4-bit
Text generation · LiquidAI ↓ 206 · ♥ 0
Params
1.2B
Weights
≈ 659 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-10-14

Qwen2.5-Coder-7B-bf16

from Qwen/Qwen2.5-7B
bf16
Text generation · Qwen ↓ 206 · ♥ 0
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-09-18

GLM-5.1-DQ4plus-q8

from zai-org/GLM-5.1
8-bit
Text generation · zai-org ↓ 205 · ♥ 6
Params
744B
Weights
≈ 791 GB
Mac memory
> 512 GB

mit · updated 2026-04-12

Qwen3.6-27B-OBLITERATED-MLX-4bit

from OBLITERATUS/Qwen3.6-27B-OBLITERATED
4-bit
Text generation · OBLITERATUS ↓ 205 · ♥ 3
Params
27B
Weights
≈ 15.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-06-09

LFM2.5-350M-OptiQ-4bit

from LiquidAI/LFM2.5-350M
4-bit
Text generation · LiquidAI ↓ 205 · ♥ 0
Params
354M
Weights
≈ 199 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-10-14

GLM-4.7-6bit

from zai-org/GLM-4.7
6-bit
Text generation · zai-org ↓ 203 · ♥ 1
Params
353B
Weights
≈ 287 GB
Mac memory
512 GB+

mit · updated 2025-12-22

Qwen3.6-35B-A3B-MTP-bf16

from Qwen/Qwen3.6-35B-A3B
bf16
Text generation · Qwen ↓ 203 · ♥ 0
Params
845M
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

Bio-Medical-Llama-3-2-1B-CoT-012025

from ContactDoctor/Bio-Medical-Llama-3-2-1B-CoT-012025
4-bit
Text generation · ContactDoctor ↓ 202 · ♥ 3
Params
1.2B
Weights
≈ 695 MB
Mac memory
8 GB+

other · updated 2025-01-26

cyberneurova-Qwen3.8-27B-8bit

from cyberneurova/cyberneurova-Qwen3.8-27B
8-bit
Text generation · cyberneurova ↓ 202 · ♥ 1
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-08-17

K2-Horizon-MoVA-36B-A4B-bf16

from IFM/K2-Horizon-MoVA-36B-A4B
bf16
Text generation · IFM ↓ 202 · ♥ 0
Params
37B
Weights
≈ 74.9 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-09-29

MiniMax-M2.5-3bit

from MiniMaxAI/MiniMax-M2.5
3-bit
Text generation · MiniMaxAI ↓ 201 · ♥ 12
Params
229B
Weights
≈ 100 GB
Mac memory
128 GB+

modified-mit · updated 2026-02-13

mistral-7B-v0.1

mlx-community/mistral-7B-v0.1
Text generation ↓ 201 · ♥ 10
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2023-12-20

DeepSeek-R1-2bit

from deepseek-ai/DeepSeek-R1
2-bit
Text generation · DeepSeek ↓ 201 · ♥ 9
Params
671B
Weights
≈ 210 GB
Mac memory
256 GB+

mit · updated 2025-03-06

Josiefied-Qwen2.5-7B-Instruct-abliterated-v2

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
Text generation · Goekdeniz-Guelmez ↓ 201 · ♥ 4
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-12-08

mini-coder-4b-OptiQ-4bit

from ricdomolm/mini-coder-4b
4-bit
Text generation · ricdomolm ↓ 201 · ♥ 2
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

mit · updated 2026-07-01

DeepSeek-V4-Flash-8bit

mlx-community/DeepSeek-V4-Flash-8bit
8-bit
Text generation ↓ 201 · ♥ 1
Params
284B
Weights
≈ 302 GB
Mac memory
512 GB+

updated 2026-04-25

Qwen3.5-4B-MTP-bf16

from Qwen/Qwen3.5-4B
bf16
Text generation · Qwen ↓ 201 · ♥ 1
Params
121M
Weights
≈ 241 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

Huihui-Qwen3.5-35B-A3B-abliterated-mxfp4

from huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated
MXFP4
Text generation · huihui-ai ↓ 200 · ♥ 3
Params
35B
Weights
≈ 19.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-03-04

plamo-2-translate-8bit

from pfnet/plamo-2-translate
8-bit
Text generation · pfnet ↓ 200 · ♥ 2
Params
9.5B
Weights
≈ 10.1 GB
Mac memory
16 GB+

plamo-community-license · updated 2026-10-07

LFM2.5-1.2B-JP-202606-OptiQ-4bit

from LiquidAI/LFM2.5-1.2B-JP-202606
4-bit
Text generation · LiquidAI ↓ 200 · ♥ 0
Params
1.2B
Weights
≈ 659 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-10-14

Qwen2.5-72B-Instruct-3bit

from Qwen/Qwen2.5-72B-Instruct
3-bit
Text generation · Qwen ↓ 200 · ♥ 0
Params
73B
Weights
≈ 31.8 GB
Mac memory
48 GB+

qwen · updated 2024-11-24

LFM2.5-1.2B-Thinking-4bit

from LiquidAI/LFM2.5-1.2B-Thinking
4-bit
Text generation · LiquidAI ↓ 199 · ♥ 0
Params
1.2B
Weights
≈ 659 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

SmolLM2-1.7B-Instruct

from HuggingFaceTB/SmolLM2-1.7B-Instruct
Text generation · Hugging Face ↓ 198 · ♥ 4
Params
1.7B
Weights
≈ 3.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-10-31

MiniCPM5-1B-4bit

from openbmb/MiniCPM5-1B
4-bit
Text generation · openbmb ↓ 198 · ♥ 1
Params
1.1B
Weights
≈ 608 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-26

bigcode-starcoder2-15b-4bit

from bigcode/starcoder2-15b
4-bit
Text generation · BigCode ↓ 198 · ♥ 0
Params
16B
Weights
≈ 9.0 GB
Mac memory
16 GB+

bigcode-openrail-m · updated 2025-02-16

Qwen3-30B-A3B-Thinking-2507-4bit

from Qwen/Qwen3-30B-A3B-Thinking-2507
4-bit
Text generation · Qwen ↓ 197 · ♥ 5
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-08-23

DeepSeek-R1-Distill-Llama-8B

from deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Text generation · DeepSeek ↓ 197 · ♥ 4
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

updated 2025-02-16

Laguna-XS.2-4bit

from poolside/Laguna-XS.2
4-bit
Text generation · poolside ↓ 197 · ♥ 4
Params
33B
Weights
≈ 18.8 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-28

Qwen2.5-1.5B-4bit

mlx-community/Qwen2.5-1.5B-4bit
4-bit
Text generation ↓ 196 · ♥ 0
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

DeepSeek-V4-Pro-bf16

mlx-community/DeepSeek-V4-Pro-bf16
bf16
Text generation ↓ 195 · ♥ 2
Params
1.6T
Weights
≈ 6241 GB
Mac memory
> 512 GB

updated 2026-05-23

gemma-4-E2B-it-qat-assistant-4bit

from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
4-bit
Text generation · Google · Gemma ↓ 195 · ♥ 0
Params
78M
Weights
≈ 45 MB
Mac memory
8 GB+

gemma · updated 2026-06-05

Josiefied-Qwen3-14B-abliterated-v3-8bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
8-bit
Text generation · Goekdeniz-Guelmez ↓ 194 · ♥ 2
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+

updated 2025-06-04

deepseek-coder-33b-instruct

from deepseek-ai/deepseek-coder-33b-instruct
4-bit
Text generation · DeepSeek ↓ 194 · ♥ 2
Params
33B
Weights
≈ 18.8 GB
Mac memory
24 GB+

deepseek · updated 2025-06-21

Qwen3-8B-4bit-AWQ

from Qwen/Qwen3-8B
4-bit
Text generation · Qwen ↓ 193 · ♥ 1
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-29

Qwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8

from Qwen/Qwen3-Coder-30B-A3B-Instruct
8-bit DWQ
Text generation · Qwen ↓ 193 · ♥ 1
Params
31B
Weights
≈ 32.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-08-01

gemma-3-270m-it-bf16

from google/gemma-3-270m-it
bf16
Text generation · Google · Gemma ↓ 192 · ♥ 2
Params
436M
Weights
≈ 872 MB
Mac memory
8 GB+

gemma · updated 2025-08-09

gemma-2b-coder

mlx-community/gemma-2b-coder
Text generation ↓ 192 · ♥ 0
Params
2.5B
Weights
≈ 9.0 GB
Mac memory
16 GB+

updated 2024-02-27

Laguna-S-2.1-oQ6e

from poolside/Laguna-S-2.1
6-bit
Text generation · poolside ↓ 191 · ♥ 7
Params
118B
Weights
≈ 95.6 GB
Mac memory
128 GB+

openmdw-1.1 · updated 2026-07-24

Llama-3.3-Swallow-70B-Instruct-v0.4-8bit

from tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4
8-bit
Text generation · tokyotech-llm ↓ 191 · ♥ 1
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3.3 · updated 2025-03-10

LFM2.5-24B-A2B-Preview-8bit

from lq-preview/LFM2.5-24B-A2B-Preview
8-bit
Text generation · lq-preview ↓ 191 · ♥ 0
Params
24B
Weights
≈ 25.5 GB
Mac memory
32 GB+

lfm1.0 · updated 2026-10-13

Qwen3-8B-3bit

from Qwen/Qwen3-8B
3-bit
Text generation · Qwen ↓ 191 · ♥ 0
Params
8.2B
Weights
≈ 3.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Moonlight-16B-A3B-Instruct-4-bit

from moonshotai/Moonlight-16B-A3B-Instruct
4-bit
Text generation · Moonshot · Kimi ↓ 190 · ♥ 4
Params
16B
Weights
≈ 9.0 GB
Mac memory
16 GB+

mit · updated 2025-02-28

Llama-3.1-70B-Japanese-Instruct-2407-8bit

mlx-community/Llama-3.1-70B-Japanese-Instruct-2407-8bit
8-bit
Text generation ↓ 190 · ♥ 1
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3.1 · updated 2024-07-26

Laguna-XS-2.1-8bit

from poolside/Laguna-XS-2.1
8-bit
Text generation · poolside ↓ 189 · ♥ 2
Params
33B
Weights
≈ 35.5 GB
Mac memory
48 GB+

openmdw-1.1 · updated 2026-07-03

Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-7B-Instruct-abliterated-v1
Text generation · Goekdeniz-Guelmez ↓ 189 · ♥ 1
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-02-16

DeepSeek-R1-Distill-Qwen-14B

from deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text generation · DeepSeek ↓ 188 · ♥ 4
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+

updated 2025-02-26

starcoder2-7b-4bit

mlx-community/starcoder2-7b-4bit
4-bit
Text generation ↓ 188 · ♥ 2
Params
7.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

bigcode-openrail-m · updated 2024-03-03

Qwen2.5-Math-72B-Instruct-4bit

from Qwen/Qwen2.5-Math-72B-Instruct
4-bit
Text generation · Qwen ↓ 187 · ♥ 1
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

qwen · updated 2024-09-18

DeepSeek-V4-Pro-8bit

mlx-community/DeepSeek-V4-Pro-8bit
8-bit
Text generation ↓ 186 · ♥ 2
Params
1.6T
Weights
≈ 1672 GB
Mac memory
> 512 GB

updated 2026-05-23