JOSIE-4B-Instruct-bfloat16
from Goekdeniz-Guelmez/JOSIE-4B-Instruct
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
mit · updated 2026-02-12
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 48 of 49 · clear filters
JOSIE-4B-Thinking-4bit
from Goekdeniz-Guelmez/JOSIE-4B-Thinking
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
mit · updated 2026-02-12
JOSIE-4B-Thinking-6bit
from Goekdeniz-Guelmez/JOSIE-4B-Thinking
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
mit · updated 2026-02-12
JOSIE-4B-Thinking-8bit
from Goekdeniz-Guelmez/JOSIE-4B-Thinking
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
mit · updated 2026-02-12
Josie-r1-4b-PoC-8bit
from Goekdeniz-Guelmez/Josie-r1-4b-PoC-bf16
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
updated 2025-12-18
Josiefied-Qwen3-0.6B-gabliterated-6bit
from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-gabliterated-v1
Params
596M
Weights
≈ 484 MB
Mac memory
8 GB+
updated 2026-01-26
Laguna-M.1-mxfp8
from poolside/Laguna-M.1
Params
226B
Weights
≈ 240 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-06-18
MiniMax-M2.1-REAP-40-8bit
from 0xSero/MiniMax-M2.1-139B
Params
139B
Weights
≈ 148 GB
Mac memory
192 GB+
apache-2.0 · updated 2026-01-14
Nanbeige4-3B-Thinking-2511-gabliterated-8bit
from Goekdeniz-Guelmez/Nanbeige4-3B-Thinking-2511-gabliterated
Params
3.9B
Weights
≈ 4.2 GB
Mac memory
8 GB+
updated 2026-01-13
Olmo-3-7B-Instruct-SFT-6bit
from allenai/Olmo-3-7B-Instruct-SFT
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-11-20
Ring-flash-linear-2.0-6bit
from inclusionAI/Ring-flash-linear-2.0
Params
104B
Weights
≈ 84.6 GB
Mac memory
128 GB+
mit · updated 2025-11-02
Rivermind-Lux-12B-v1-4bit
from TheDrummer/Rivermind-Lux-12B-v1
Params
12B
Weights
≈ 6.9 GB
Mac memory
16 GB+
updated 2025-06-06
SU-01-8bit
from Simplified-Reasoning/SU-01
Params
31B
Weights
≈ 32.4 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-05-17
XortronCriminalComputingConfig-8bit
from darkc0de/XortronCriminalComputingConfig
Params
24B
Weights
≈ 25.0 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-02-19
XortronCriminalComputingConfig-bfloat16
from darkc0de/XortronCriminalComputingConfig
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+
apache-2.0 · updated 2026-02-18
deepcogito-cogito-v1-preview-llama-3B-bf16
from deepcogito/cogito-v1-preview-llama-3B
Params
3.2B
Weights
≈ 6.4 GB
Mac memory
16 GB+
llama3.2 · updated 2025-04-08
deepcogito-cogito-v1-preview-llama-8B-6bit
from deepcogito/cogito-v1-preview-llama-8B
Params
8.0B
Weights
≈ 6.5 GB
Mac memory
16 GB+
llama3.1 · updated 2025-04-08
deepcogito-cogito-v1-preview-qwen-14B-bf16
from deepcogito/cogito-v1-preview-qwen-14B
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-04-08
gemma-3-270m-6bit
from google/gemma-3-270m
Params
436M
Weights
≈ 354 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
gemma-3-270m-qat-8bit
from google/gemma-3-270m-qat
Params
436M
Weights
≈ 463 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
qwq-bakeneko-32b-4bit
from rinna/qwq-bakeneko-32b
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-13
Falcon3-3B-Instruct-3bit
from tiiuae/Falcon3-3B-Instruct
Params
3.2B
Weights
≈ 1.4 GB
Mac memory
8 GB+
falcon-llm-license · updated 2024-12-17
Fathom-R1-14B-4bit
from FractalAIResearch/Fathom-R1-14B
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
mit · updated 2025-06-06
JOSIE-1.1-4B-Instruct-mxfp4
from Goekdeniz-Guelmez/JOSIE-1.1-4B-Instruct
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
mit · updated 2026-03-09
JOSIE-1.1-4B-Thinking-4bit
from Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
mit · updated 2026-03-09
JOSIE-1.1-4B-Thinking-mxfp4
from Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
mit · updated 2026-03-09
Josie-r1-4b-4bit
from Goekdeniz-Guelmez/Josie-r1-4b
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
updated 2025-12-18
Josie-r1-4b-bfloat16
from Goekdeniz-Guelmez/Josie-r1-4b
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
updated 2025-12-18
Josiefied-Qwen3-0.6B-gabliterated-8bit
from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-gabliterated-v1
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+
updated 2026-01-26
Kumru-2B-6bit
from vngrs-ai/Kumru-2B
Params
2.4B
Weights
≈ 1.9 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-15
LFM2-2.6B-Exp-5bit
from LiquidAI/LFM2-2.6B-Exp
Params
2.6B
Weights
≈ 1.8 GB
Mac memory
8 GB+
lfm1.0 · updated 2025-12-26
LFM2.5-1.2B-Base-8bit
from LiquidAI/LFM2.5-1.2B-Base
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+
other · updated 2026-01-06
LFM2.5-1.2B-JP-6bit
from LiquidAI/LFM2.5-1.2B-JP
Params
1.2B
Weights
≈ 951 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-01-06
Llama-3-Karamaru-v1-8bit
from SakanaAI/Llama-3-Karamaru-v1
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2025-04-01
Nanbeige4-3B-Thinking-2511-gabliterated-6bit
from Goekdeniz-Guelmez/Nanbeige4-3B-Thinking-2511-gabliterated
Params
3.9B
Weights
≈ 3.2 GB
Mac memory
8 GB+
updated 2026-01-13
Olmo-3-7B-Instruct-6bit
from allenai/Olmo-3-7B-Instruct
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-11-20
Olmo-3-7B-RLZero-Mix-8bit
from allenai/Olmo-3-7B-RL-Zero-General
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-11-21
QwQ-0.5B-8bit
from InfiniAILab/QwQ-0.5B
Params
494M
Weights
≈ 525 MB
Mac memory
8 GB+
updated 2025-04-07
SERA-32B-8bit
from allenai/SERA-32B
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-01-28
SU-01-4bit
from Simplified-Reasoning/SU-01
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-05-16
SU-01-5bit
from Simplified-Reasoning/SU-01
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-05-16
Smaug-Llama-3-70B-Instruct-4bit
mlx-community/Smaug-Llama-3-70B-Instruct-4bit
Params
11B
Weights
≈ 9.4 GB
Mac memory
16 GB+
llama3 · updated 2024-06-12
Virtuoso-Medium-v2-bf16
from arcee-ai/Virtuoso-Medium-v2
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-01-31
deepcogito-cogito-v1-preview-llama-8B-fp16
from deepcogito/cogito-v1-preview-llama-8B
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3.1 · updated 2025-04-08
granite-philosophy-mlx
mlx-community/granite-philosophy-mlx
Params
352M
Weights
≈ 883 MB
Mac memory
8 GB+
updated 2026-01-10
mamba-370m-hf-f32
from state-spaces/mamba-370m-hf
Params
372M
Weights
≈ 1.5 GB
Mac memory
8 GB+
updated 2024-09-21
mamba-790m-hf-f16
from state-spaces/mamba-790m-hf
Params
793M
Weights
≈ 1.6 GB
Mac memory
8 GB+
updated 2024-09-21
threemistrals-6bit
from mstyslavity/dead_covvard
Params
7.2B
Weights
≈ 5.9 GB
Mac memory
16 GB+
updated 2026-01-10
SERA-32B-6bit
from allenai/SERA-32B
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-01-28
LLaDA-8B-Instruct-mlx-fp16
from GSAI-ML/LLaDA-8B-Instruct
Params
8.0B
Weights
≈ 16.0 GB
Mac memory
24 GB+
mit · updated 2025-03-12
g2p-multilingual-byT5-tiny-mlx
from charsiu/g2p_multilingual_byT5_tiny_16_layers_100
Params
21M
Weights
≈ 83 MB
Mac memory
8 GB+
mit · updated 2026-03-21
EXAONE-Deep-32B-mlx-8Bit
from LGAI-EXAONE/EXAONE-Deep-32B
Params
32B
Weights
≈ 34.0 GB
Mac memory
48 GB+
exaone · updated 2025-03-21
JOSIE-1.1-4B-Thinking-8bit
from Goekdeniz-Guelmez/JOSIE-1.1-4B-Thinking
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
mit · updated 2026-03-09
Olmo-3-7B-RLZero-Code-8bit
from allenai/Olmo-3-7B-RL-Zero-Code
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-11-25
Olmo-3-7B-RLZero-Mix-bfloat16
from allenai/Olmo-3-7B-RL-Zero-General
Params
7.3B
Weights
≈ 14.6 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-11-20
QwQ-0.5B-fp16
from InfiniAILab/QwQ-0.5B
Params
494M
Weights
≈ 988 MB
Mac memory
8 GB+
updated 2025-04-07
SERA-8B-GA-8bit
from allenai/SERA-8B-GA
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+
updated 2026-01-27
gemma-3-270m-it-qat-bf16
from google/gemma-3-270m-it-qat
Params
436M
Weights
≈ 872 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
granite-4.0-h-350m-base-bf16
from ibm-granite/granite-4.0-h-350m-base
Params
340M
Weights
≈ 681 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
mamba-1.4b-hf-f32
from state-spaces/mamba-1.4b-hf
Params
1.4B
Weights
≈ 5.5 GB
Mac memory
16 GB+
updated 2024-09-21