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 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 49 of 49 · clear filters

JOSIE-4B-Instruct-4bit

from Goekdeniz-Guelmez/JOSIE-4B-Instruct
4-bit
Text generation · Goekdeniz-Guelmez ↓ 15 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

mit · updated 2026-02-12

JOSIE-IT1-Qwen3-0.6B-6bit

from Goekdeniz-Guelmez/JOSIE-IT1-Qwen3-0.6B
6-bit
Text generation · Goekdeniz-Guelmez ↓ 15 · ♥ 0
Params
596M
Weights
≈ 484 MB
Mac memory
8 GB+

updated 2026-01-12

Olmo-3-7B-RLZero-Mix-6bit

from allenai/Olmo-3-7B-RL-Zero-General
6-bit
Text generation · Ai2 · OLMo ↓ 15 · ♥ 0
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-21

SERA-8B-GA-5bit

from allenai/SERA-8B-GA
5-bit
Text generation · Ai2 · OLMo ↓ 15 · ♥ 0
Params
8.2B
Weights
≈ 5.6 GB
Mac memory
16 GB+

updated 2026-01-27

SU-01-bf16

from Simplified-Reasoning/SU-01
bf16
Text generation · Simplified-Reasoning ↓ 15 · ♥ 0
Params
31B
Weights
≈ 61.1 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-05-16

SU-01-nvfp4

from Simplified-Reasoning/SU-01
4-bit
Text generation · Simplified-Reasoning ↓ 15 · ♥ 0
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-05-16

Skywork-SWE-32B-6bit

from Skywork/Skywork-SWE-32B
6-bit
Text generation · Skywork ↓ 15 · ♥ 0
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-06-19

XBai-o4-6bit

from MetaStoneTec/XBai-o4
6-bit
Text generation · MetaStoneTec ↓ 15 · ♥ 0
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-08-02

talkie-box-6bit

mlx-community/talkie-box-6bit
6-bit
Text generation ↓ 15 · ♥ 0
Params
13B
Weights
≈ 11.2 GB
Mac memory
16 GB+

updated 2026-04-30

MiroThinker-32B-DPO-v0.1-4bit-8k

from miromind-ai/MiroThinker-32B-DPO-v0.1
4-bit
Text generation · miromind-ai ↓ 14 · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-08-15

XBai-o4-4bit-DWQ

from MetaStoneTec/XBai-o4
4-bit DWQ
Text generation · MetaStoneTec ↓ 14 · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-08-02

JOSIE-IT1-Qwen3-0.6B-8bit

from Goekdeniz-Guelmez/JOSIE-IT1-Qwen3-0.6B
8-bit
Text generation · Goekdeniz-Guelmez ↓ 14 · ♥ 0
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+

updated 2026-01-12

Josie-r1-4b-6bit

from Goekdeniz-Guelmez/Josie-r1-4b
6-bit
Text generation · Goekdeniz-Guelmez ↓ 14 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

updated 2025-12-18

MiniMax-M2.1-REAP-30-8bit

from 0xSero/MiniMax-M2.1-162B
8-bit
Text generation · 0xSero ↓ 14 · ♥ 0
Params
162B
Weights
≈ 172 GB
Mac memory
256 GB+

apache-2.0 · updated 2026-01-14

Olmo-3-1125-32B-bfloat16

from allenai/Olmo-3-1125-32B
Text generation · Ai2 · OLMo ↓ 14 · ♥ 0
Params
32B
Weights
≈ 64.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-11-21

Rivermind-Lux-12B-v1-6bit

from TheDrummer/Rivermind-Lux-12B-v1
6-bit
Text generation · TheDrummer ↓ 14 · ♥ 0
Params
12B
Weights
≈ 10.0 GB
Mac memory
16 GB+

updated 2025-06-06

SERA-32B-5bit

from allenai/SERA-32B
5-bit
Text generation · Ai2 · OLMo ↓ 14 · ♥ 0
Params
33B
Weights
≈ 22.5 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-01-27

SU-01-mxfp8

from Simplified-Reasoning/SU-01
MXFP8
Text generation · Simplified-Reasoning ↓ 14 · ♥ 0
Params
31B
Weights
≈ 32.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-05-16

granite-4.0-350m-base-bf16

from ibm-granite/granite-4.0-350m-base
bf16
Text generation · IBM · Granite ↓ 14 · ♥ 0
Params
352M
Weights
≈ 705 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

Josie-r1-4b-8bit

from Goekdeniz-Guelmez/Josie-r1-4b
8-bit
Text generation · Goekdeniz-Guelmez ↓ 13 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2025-12-18

SERA-8B-GA-bf16

from allenai/SERA-8B-GA
bf16
Text generation · Ai2 · OLMo ↓ 13 · ♥ 0
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+

updated 2026-01-27

SERA-32B-GA-6bit

from allenai/SERA-32B-GA
6-bit
Text generation · Ai2 · OLMo ↓ 12 · ♥ 0
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-01-28

SERA-32B-GA-8bit

from allenai/SERA-32B-GA
8-bit
Text generation · Ai2 · OLMo ↓ 12 · ♥ 0
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-01-28

SU-01-6bit

from Simplified-Reasoning/SU-01
6-bit
Text generation · Simplified-Reasoning ↓ 12 · ♥ 0
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-05-16

XBai-o4-5bit

from MetaStoneTec/XBai-o4
5-bit
Text generation · MetaStoneTec ↓ 12 · ♥ 0
Params
33B
Weights
≈ 22.5 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-08-02

SERA-32B-GA-5bit

from allenai/SERA-32B-GA
5-bit
Text generation · Ai2 · OLMo ↓ 11 · ♥ 0
Params
33B
Weights
≈ 22.5 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-01-27

SERA-32B-GA-bf16

from allenai/SERA-32B-GA
bf16
Text generation · Ai2 · OLMo ↓ 10 · ♥ 0
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-01-28

Meta-Llama-3-8B-4bit-conversation-finetuned

mlx-community/Meta-Llama-3-8B-4bit-conversation-finetuned
4-bit
Text generation ↓ 3 · ♥ 0
Params
8.0B
Weights
≈ 5.3 GB
Mac memory
8 GB+

llama3 · updated 2024-04-19 · gated

plamo-2-8b

from pfnet/plamo-2-8b
Text generation · pfnet ↓ 2 · ♥ 2
Params
9.1B
Weights
≈ 36.5 GB
Mac memory
48 GB+

plamo-community-license · updated 2025-03-16 · gated

VyvoTTS-EN-Beta-fp16

mlx-community/VyvoTTS-EN-Beta-fp16
fp16
Text generation ↓ 2 · ♥ 1
Params
1.8B
Weights
≈ 3.6 GB
Mac memory
8 GB+

updated 2025-12-18 · gated

VyvoTTS-EN-Beta-5bit

mlx-community/VyvoTTS-EN-Beta-5bit
5-bit
Text generation ↓ 2 · ♥ 0
Params
1.8B
Weights
≈ 1.2 GB
Mac memory
8 GB+

updated 2025-12-18 · gated

VyvoTTS-EN-Beta-6bit

mlx-community/VyvoTTS-EN-Beta-6bit
6-bit
Text generation ↓ 2 · ♥ 0
Params
1.8B
Weights
≈ 1.4 GB
Mac memory
8 GB+

updated 2025-12-18 · gated

VyvoTTS-EN-Beta-8bit

mlx-community/VyvoTTS-EN-Beta-8bit
8-bit
Text generation ↓ 2 · ♥ 0
Params
1.8B
Weights
≈ 1.9 GB
Mac memory
8 GB+

updated 2025-12-18 · gated

DeepSeek-R1-Distill-Qwen-32B-MLX

from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text generation · DeepSeek ↓ 0 · ♥ 3
Params
—
Weights
—
Mac memory
—

updated 2025-03-10

plamo-2-8b-4bit

from pfnet/plamo-2-8b
4-bit
Text generation · pfnet ↓ 0 · ♥ 3
Params
9.1B
Weights
≈ 5.1 GB
Mac memory
8 GB+

plamo-community-license · updated 2025-03-15 · gated

DeepSeek-R1-Distill-Qwen-1.5B-MLX

from deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Text generation · DeepSeek ↓ 0 · ♥ 2
Params
—
Weights
—
Mac memory
—

updated 2025-03-10

josie-1.1-4b-mlx-OptiQ-4bit

from mlx-community/JOSIE-1.1-4B-Instruct-bfloat16
4-bit
Text generation ↓ 0 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-05-14

plamo-2-8b-bf16

from pfnet/plamo-2-8b
bf16
Text generation · pfnet ↓ 0 · ♥ 2
Params
9.1B
Weights
≈ 18.2 GB
Mac memory
24 GB+

plamo-community-license · updated 2025-03-16 · gated

DeepSeek-R1-Distill-Qwen-14B-MLX

from deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
Text generation · DeepSeek ↓ 0 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2025-03-10

DeepSeek-R1-Distill-Qwen-7B-MLX

from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Text generation · DeepSeek ↓ 0 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2025-03-10

Nemotron-3-Ultra-550B-A55B-bf16

from nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
bf16
Text generation · NVIDIA ↓ 0 · ♥ 0
Params
—
Weights
—
Mac memory
—

nvidia-open-model-license · updated 2026-06-04