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

14 builds · clear filters

Qwen3.5-0.8B-decision

from Qwen/Qwen3.5-0.8B
Text classification · Qwen ↓ 1.7K · ♥ 7
Params
873M
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-23

gemma-4-e2b-it-OptiQ-4bit-decision

from mlx-community/gemma-4-e2b-it-OptiQ-4bit
4-bit
Text classification ↓ 1.1K · ♥ 5
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+

gemma · updated 2026-10-23

pplx-decider-v1.1-27b-4bit

from perplexity-ai/pplx-decider-v1.1-27b
4-bit
Text classification · perplexity-ai ↓ 734 · ♥ 6
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-07

d1a-e2b-it-qat-4bit

from google/gemma-4-E2B-it-qat-w4a16-ct
4-bit
Text classification · Google · Gemma ↓ 356 · ♥ 2
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-11

clef-flash-OptiQ-4bit

from Cloudflare/clef-flash
4-bit
Text classification · Cloudflare ↓ 326 · ♥ 3
Params
9.0B
Weights
≈ 6.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-23

clef-OptiQ-4bit

from Cloudflare/clef
4-bit
Text classification · Cloudflare ↓ 279 · ♥ 4
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-23

Jev-Style-0.8B-Decision-v3-mlx-8bit

from chaoliangUNSW/Jev-Style-0.8B-Decision-v3
8-bit
Text classification · chaoliangUNSW ↓ 271 · ♥ 0
Params
752M
Weights
≈ 800 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-14

Jev-Style-0.8B-Decision-v3-mlx-16bit

from chaoliangUNSW/Jev-Style-0.8B-Decision-v3
16-bit
Text classification · chaoliangUNSW ↓ 182 · ♥ 0
Params
752M
Weights
≈ 1.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-14

d1a-e4b-it-qat-4bit

from google/gemma-4-E4B-it-qat-w4a16-ct
4-bit
Text classification · Google · Gemma ↓ 164 · ♥ 0
Params
7.5B
Weights
≈ 4.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-11

d1a-e4b-it-8bit

from JohnP1/d1a-e4b-it
8-bit
Text classification · JohnP1 ↓ 133 · ♥ 0
Params
7.5B
Weights
≈ 7.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-25

d1-2B-OptiQ-4bit

from LiquidAI/d1-2B
4-bit
Text classification · LiquidAI ↓ 121 · ♥ 1
Params
1.7B
Weights
≈ 973 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-10-30

d1a-e2b-8bit

from JohnP1/d1a-e2b
8-bit
Text classification · JohnP1 ↓ 115 · ♥ 0
Params
4.6B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-25

d1a-e2b-it-8bit

from JohnP1/d1a-e2b-it
8-bit
Text classification · JohnP1 ↓ 102 · ♥ 0
Params
4.6B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-25

d1a-e4b-8bit

from JohnP1/d1a-e4b
8-bit
Text classification · JohnP1 ↓ 93 · ♥ 0
Params
7.5B
Weights
≈ 7.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-25