zephyr-7b-gemma-v0.1-4bit
from HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
Params
2.8B
Weights
≈ 1.8 GB
Mac memory
8 GB+
gemma-terms-of-use · updated 2024-03-02
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 25 of 49 · clear filters
QwQ-32B-Preview-bf16
from Qwen/QwQ-32B-Preview
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2024-11-27
Jan-v1-4B-8bit
from janhq/Jan-v1-4B
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-08-12
gemma-2-2b-jpn-it-4bit
from google/gemma-2-2b-it
Params
2.6B
Weights
≈ 1.5 GB
Mac memory
8 GB+
gemma · updated 2024-10-03
DeepSeek-Prover-V2-7B-bf16
from deepseek-ai/DeepSeek-Prover-V2-7B
Params
6.9B
Weights
≈ 13.8 GB
Mac memory
24 GB+
updated 2025-06-02
Ling-2.6-flash-mlx-4bit
from inclusionAI/Ling-2.6-flash
Params
104B
Weights
≈ 58.6 GB
Mac memory
96 GB+
mit · updated 2026-04-29
Ornith-1.0-9B-bf16
from deepreinforce-ai/Ornith-1.0-9B
Params
9.4B
Weights
≈ 18.8 GB
Mac memory
24 GB+
mit · updated 2026-06-28
codegemma-1.1-7b-it-6bit
from google/codegemma-1.1-7b-it
Params
8.5B
Weights
≈ 6.9 GB
Mac memory
16 GB+
gemma · updated 2025-06-01
gemma-3-text-4b-pt-4bit
from mlx-community/gemma-3-4b-pt-bf16
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+
gemma · updated 2025-03-18
granite-4.1-3b-bf16
from ibm-granite/granite-4.1-3b
Params
3.4B
Weights
≈ 6.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-04-30
Llama-3.1-Swallow-8B-Instruct-v0.2
from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3.1 · updated 2024-11-11
OLMo-2-1124-13B-Instruct-8bit
from allenai/OLMo-2-1124-13B-Instruct
Params
14B
Weights
≈ 14.6 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-11-27
OLMoE-1B-7B-0125-Instruct-8bit
from allenai/OLMoE-1B-7B-0125-Instruct
Params
6.9B
Weights
≈ 7.4 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-04
Qwen-AgentWorld-35B-A3B-oQ3.5
from Qwen/Qwen-AgentWorld-35B-A3B
Params
35B
Weights
≈ 15.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-06-27
Qwen1.5-0.5B-Chat
mlx-community/Qwen1.5-0.5B-Chat
Params
620M
Weights
≈ 1.2 GB
Mac memory
8 GB+
tongyi-qianwen-research · updated 2024-03-07
Qwen2.5-Math-7B-Instruct-8bit
from Qwen/Qwen2.5-Math-7B-Instruct
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-03
Sky-T1-32B-Preview
from NovaSky-AI/Sky-T1-32B-Preview
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
updated 2025-01-13
aya-expanse-8b-4bit-mlx
from CohereLabs/aya-expanse-8b
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
cc-by-nc-4.0 · updated 2024-12-23
granite-4.0-350m-8bit
from ibm-granite/granite-4.0-350m
Params
352M
Weights
≈ 374 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
granite-8b-code-base-4bit
mlx-community/granite-8b-code-base-4bit
Params
8.1B
Weights
≈ 4.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-05-06
Meta-Llama-3-8B-8bit
mlx-community/Meta-Llama-3-8B-8bit
Params
8.0B
Weights
≈ 9.0 GB
Mac memory
16 GB+
llama3 · updated 2024-04-18
GLM-4.5-Air-mxfp4
from zai-org/GLM-4.5-Air
Params
107B
Weights
≈ 60.1 GB
Mac memory
96 GB+
mit · updated 2025-09-26
Llama-3_3-Nemotron-Super-49B-v1-mlx-4bit
from nvidia/Llama-3_3-Nemotron-Super-49B-v1
Params
50B
Weights
≈ 28.1 GB
Mac memory
48 GB+
nvidia-open-model-license · updated 2025-04-08
Arcee-Blitz-4bit
from arcee-ai/Arcee-Blitz
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-02-20
DeepSeek-V3-0324-5bit
from deepseek-ai/DeepSeek-V3-0324
Params
671B
Weights
≈ 461 GB
Mac memory
> 512 GB
mit · updated 2025-07-06
Hunyuan-1.8B-Instruct-4bit
from tencent/Hunyuan-1.8B-Instruct
Params
1.8B
Weights
≈ 1.0 GB
Mac memory
8 GB+
updated 2025-08-04
Qwen3-0.6B-gabliterated-4bit
from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+
updated 2026-01-06
codegemma-1.1-2b-6bit
from google/codegemma-1.1-2b
Params
2.5B
Weights
≈ 2.0 GB
Mac memory
8 GB+
gemma · updated 2025-06-01
Deutscher-Pantheon-12B-4bit
from mergekit-community/Deutscher-Pantheon-12B
Params
12B
Weights
≈ 6.9 GB
Mac memory
16 GB+
updated 2025-06-03
Dolphin3.0-R1-Mistral-24B-6bit
from dphn/Dolphin3.0-R1-Mistral-24B
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+
updated 2025-03-06
EuroLLM-22B-Instruct-2512-mlx-6bit
from utter-project/EuroLLM-22B-Instruct-2512
Params
23B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-12-16
GLM-4.5-Air-5bit
from zai-org/GLM-4.5-Air
Params
107B
Weights
≈ 73.5 GB
Mac memory
96 GB+
mit · updated 2025-07-28
Goedel-Prover-V2-32B-8bit
from Goedel-LM/Goedel-Prover-V2-32B
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-01-26
Jan-nano-128k-8bit
from Menlo/Jan-nano-128k
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-06-26
Llama-3-Aplite-Instruct-4x8B-MoE-4bit
from meta-llama/Meta-Llama-3-8B-Instruct
Params
25B
Weights
≈ 14.0 GB
Mac memory
24 GB+
llama3 · updated 2024-04-26
Mistral-7B-v0.1-q
mlx-community/Mistral-7B-v0.1-q
Params
7.2B
Weights
≈ 28.7 GB
Mac memory
48 GB+
apache-2.0 · updated 2024-02-25
Qwen3-4B-Instruct-2507-gabliterated-6bit
from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
updated 2026-01-06
Qwen3-4B-Sky-High-Hermes-gabliterated-8bit
from Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
updated 2026-01-23
SmolLM3-3B-abliterated-bf16
from HuggingFaceTB/SmolLM3-3B
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-07-10
gemma-3-12b-pt-4bit-text
from google/gemma-3-12b-pt
Params
12B
Weights
≈ 6.6 GB
Mac memory
16 GB+
gemma · updated 2026-02-23
Qwen3-30B-A3B-4bit-DWQ-05082025
from Qwen/Qwen3-30B-A3B
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-05-08
gemma-3-27b-it-4bit-DWQ
from google/gemma-3-27b-it
Params
28B
Weights
≈ 16.0 GB
Mac memory
24 GB+
gemma · updated 2025-05-14
granite-4.0-h-tiny-5bit-MLX
from ibm-granite/granite-4.0-h-tiny
Params
6.9B
Weights
≈ 4.8 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-03
mxbai-rerank-large-v2
from mixedbread-ai/mxbai-rerank-large-v2
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-07-23
Apertus-8B-Instruct-2509-6bit
from swiss-ai/Apertus-8B-Instruct-2509
Params
8.1B
Weights
≈ 6.5 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-09-03
Falcon3-7B-Instruct-1.58bit-4bit
from tiiuae/Falcon3-7B-Instruct-1.58bit
Params
3.5B
Weights
≈ 3.8 GB
Mac memory
8 GB+
falcon-llm-license · updated 2025-06-10
Llama-3.1-Tulu-3-8B-8bit
from allenai/Llama-3.1-Tulu-3-8B
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3.1 · updated 2024-11-25
Meta-Llama-3.1-8B-bf16
mlx-community/Meta-Llama-3.1-8B-bf16
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3.1 · updated 2024-07-23
AIDC-AI_Marco-o1_MLX-8bit
from ATH-MaaS/Marco-o1
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-11-27
DeepSeek-Prover-V2-7B-8bit
from deepseek-ai/DeepSeek-Prover-V2-7B
Params
6.9B
Weights
≈ 7.3 GB
Mac memory
16 GB+
updated 2025-06-02
Falcon-H1-Tiny-Multilingual-100M-Instruct-4bit
from tiiuae/Falcon-H1-Tiny-Multilingual-100M-Instruct
Params
108M
Weights
≈ 61 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
GLM-Z1-9B-0414-6bit
from zai-org/GLM-Z1-9B-0414
Params
9.4B
Weights
≈ 7.6 GB
Mac memory
16 GB+
mit · updated 2025-04-21
GLM-Z1-9B-0414-8bit
from zai-org/GLM-Z1-9B-0414
Params
9.4B
Weights
≈ 10.0 GB
Mac memory
16 GB+
mit · updated 2025-04-21
Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-8bit
from Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1
Params
494M
Weights
≈ 525 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-11-17
Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-8-bit
from Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-12-08
Josiefied-Qwen3.5-0.8B-gabliterated-v1-mxfp4
from Goekdeniz-Guelmez/Josiefied-Qwen3.5-0.8B-gabliterated-v1
Params
752M
Weights
≈ 424 MB
Mac memory
8 GB+
updated 2026-03-13
Mixtral-SlimOrca-8x7B-3bit
from Open-Orca/Mixtral-SlimOrca-8x7B
Params
47B
Weights
≈ 20.4 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-02-19
OLMo-2-1124-7B-Instruct-8bit
from allenai/OLMo-2-1124-7B-Instruct
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-11-27
Qwen2.5-32B-bf16
mlx-community/Qwen2.5-32B-bf16
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2024-09-18
Qwen2.5-Math-72B-Instruct-8bit
from Qwen/Qwen2.5-Math-72B
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+
qwen · updated 2024-09-19