Hy3-preview-4bit
from tencent/Hy3-preview
Params
295B
Weights
≈ 166 GB
Mac memory
192 GB+
other · updated 2026-04-27
Apple silicon
Apple MLX models
5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 24m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 20 of 49 · clear filters
Qwen2-7B-Instruct-8bit
mlx-community/Qwen2-7B-Instruct-8bit
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-06-06
Mistral-7B-v0.1-hf-4bit-mlx
mlx-community/Mistral-7B-v0.1-hf-4bit-mlx
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2024-01-07
Josiefied-Qwen3-30B-A3B-abliterated-v2-8bit
from Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2
Params
31B
Weights
≈ 32.4 GB
Mac memory
48 GB+
updated 2025-06-19
Josiefied-Qwen3-8B-abliterated-v1-8bit
from Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+
updated 2025-05-02
Mistral-NeMo-Minitron-8B-Instruct-4bit
from nvidia/Mistral-NeMo-Minitron-8B-Base
Params
8.4B
Weights
≈ 4.7 GB
Mac memory
8 GB+
nvidia-community-model-license · updated 2024-10-04
Nanbeige4.1-3B-4bit
from Nanbeige/Nanbeige4.1-3B
Params
3.9B
Weights
≈ 2.2 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-02-23
QwQ-Qwen2.5-Coder-Instruct-32B-4bit
from sm54/QwQ-Qwen2.5-Coder-Instruct-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
updated 2025-03-09
Qwen3-30B-A3B-6bit
from Qwen/Qwen3-30B-A3B
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-04-28
SmolLM3-3B-4bit-DWQ
from HuggingFaceTB/SmolLM3-3B
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-07-09
Dracarys2-72B-Instruct-4bit
from abacusai/Dracarys2-72B-Instruct
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+
tongyi-qianwen · updated 2024-10-06
ERNIE-4.5-21B-A3B-PT-4bit
from mlx-community/ERNIE-4.5-21B-A3B-PT-bf16
Params
22B
Weights
≈ 12.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-07-10
GLM-4.5-Air-mxfp8
from zai-org/GLM-4.5-Air
Params
107B
Weights
≈ 114 GB
Mac memory
192 GB+
mit · updated 2026-05-06
Mellum2-12B-A2.5B-Instruct-8bit
from JetBrains/Mellum2-12B-A2.5B-Instruct
Params
12B
Weights
≈ 12.9 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-08-11
Qwen2.5-32B-4bit
mlx-community/Qwen2.5-32B-4bit
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-09-18
glm-4-9b-chat-1m-4bit
from zai-org/glm-4-9b-chat-1m-hf
Params
9.5B
Weights
≈ 5.3 GB
Mac memory
8 GB+
glm-4 · updated 2025-09-14
karakuri-lm-8x7b-chat-v0.1
from karakuri-ai/karakuri-lm-8x7b-chat-v0.1
Params
47B
Weights
≈ 93.4 GB
Mac memory
128 GB+
apache-2.0 · updated 2024-10-11
Qwen_QwQ-32B-Preview_MLX-8bit
from Qwen/QwQ-32B-Preview
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2024-11-28
Viper-Coder-v1.1-4bit
from prithivMLmods/Viper-Coder-v1.1
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-02-21
gemma-3-1b-pt-4bit
from google/gemma-3-1b-pt
Params
1.3B
Weights
≈ 732 MB
Mac memory
8 GB+
gemma · updated 2025-03-12
granite-8b-code-base-8bit
mlx-community/granite-8b-code-base-8bit
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-05-06
llm-jp-3-13b-instruct-4bit
mlx-community/llm-jp-3-13b-instruct-4bit
Params
14B
Weights
≈ 7.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-09-25
JOSIE-1.1-4B-Instruct-4bit
from Goekdeniz-Guelmez/JOSIE-1.1-4B-Instruct
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
mit · updated 2026-03-09
Qwen3-1.7B-5bit
from Qwen/Qwen3-1.7B
Params
1.7B
Weights
≈ 1.2 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-05-15
VulnLLM-R-7B-4bit
from Virtue-AI-HUB/VulnLLM-R-7B
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-01-02
gemma-3n-E2B-it-lm-bf16
from google/gemma-3n-E2B-it
Params
4.5B
Weights
≈ 8.9 GB
Mac memory
16 GB+
gemma · updated 2025-06-29
llm-jp-3-8x13b-instruct3
from llm-jp/llm-jp-3-8x13b-instruct3
Params
73B
Weights
≈ 146 GB
Mac memory
192 GB+
apache-2.0 · updated 2025-03-28
QwQ-32B-8bit
from Qwen/QwQ-32B
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-03-05
DeepSeek-V3.1-Base-4bit
from deepseek-ai/DeepSeek-v3.1-Base
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+
mit · updated 2025-08-20
LFM2-2.6B-8bit
from LiquidAI/LFM2-2.6B
Params
2.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+
lfm1.0 · updated 2025-09-25
MiniMax-M2.7
from MiniMaxAI/MiniMax-M2.7
Params
229B
Weights
≈ 457 GB
Mac memory
> 512 GB
modified-mit · updated 2026-04-12
Qwen3-30B-A3B-Thinking-2507-bf16
from Qwen/Qwen3-30B-A3B-Thinking-2507
Params
31B
Weights
≈ 61.1 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-08-01
Qwen3-30B-A3B-mixed-3-4bit
from Qwen/Qwen3-30B-A3B
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-05-02
Llama-3-Groq-8B-Tool-Use-8bit
mlx-community/Llama-3-Groq-8B-Tool-Use-8bit
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2024-07-17
Qwen2.5-7B-Medicine-4bit
from WangCa/Qwen2.5-7B-Medicine
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
mit · updated 2025-06-03
Qwen2.5-Coder-32B-bf16
from Qwen/Qwen2.5-Coder-32B
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2024-11-12
gemma-4-26B-A4B-it-qat-assistant-mxfp4
from google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant
Params
420M
Weights
≈ 236 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
phi-4-2bit
from microsoft/phi-4
Params
15B
Weights
≈ 4.6 GB
Mac memory
8 GB+
mit · updated 2025-01-12
ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-4bit
from abeja/ABEJA-Qwen3-14B-Agentic-256k-v0.1
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-28
GLM-4.7-Flash-Derestricted-8bit-gs32
from koute/GLM-4.7-Flash-Derestricted
Params
30B
Weights
≈ 31.8 GB
Mac memory
48 GB+
mit · updated 2026-01-26
Olmo-3-7B-Think-4bit
from allenai/Olmo-3-7B-Think
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-11-21
Qwen3-0.6B-3bit
from Qwen/Qwen3-0.6B
Params
596M
Weights
≈ 261 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-04-28
c4ai-command-r7b-12-2024-8bit
from CohereLabs/c4ai-command-r7b-12-2024
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
cc-by-nc-4.0 · updated 2024-12-15
magnum-v2-72b
from anthracite-org/magnum-v2-72b
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+
tongyi-qianwen · updated 2024-10-14
shisa-v2.1-llama3.3-70b-mlx-bf16
from shisa-ai/shisa-v2.1-llama3.3-70b
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+
llama3.3 · updated 2025-12-16
gemma-2-2b-4bit
mlx-community/gemma-2-2b-4bit
Params
2.6B
Weights
≈ 1.5 GB
Mac memory
8 GB+
gemma · updated 2024-07-31
Llama-3-Groq-8B-Tool-Use-bf16
mlx-community/Llama-3-Groq-8B-Tool-Use-bf16
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3 · updated 2024-07-17
Ring-mini-linear-2.0-4bit
from inclusionAI/Ring-mini-linear-2.0
Params
16B
Weights
≈ 9.2 GB
Mac memory
16 GB+
mit · updated 2025-10-02
AREX-Turbo-4bit
from BAAI/AREX-Turbo
Params
4.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-07-28
codegemma-1.1-2b-4bit
from google/codegemma-1.1-2b
Params
2.5B
Weights
≈ 1.4 GB
Mac memory
8 GB+
gemma · updated 2025-06-02
llm-jp-3-8x1.8b-instruct3-4bit
from llm-jp/llm-jp-3-8x1.8b-instruct3
Params
9.3B
Weights
≈ 5.2 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-03-27
llm-jp-4-8b-thinking-8bit
from llm-jp/llm-jp-4-8b-thinking
Params
8.6B
Weights
≈ 9.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-04-12
1.5-Pints-2K-v0.1
from pints-ai/1.5-Pints-2K-v0.1
Params
1.6B
Weights
≈ 3.1 GB
Mac memory
8 GB+
mit · updated 2024-10-28
Dobby-Unhinged-Llama-3.3-70B-mlx-4Bit
from SentientAGI/Dobby-Unhinged-Llama-3.3-70B
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+
llama3.3 · updated 2025-09-15
Llama-3.1-Tulu-3-70B-4bit
from allenai/Llama-3.1-Tulu-3-70B
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+
llama3.1 · updated 2024-11-25
Mellum2-12B-A2.5B-Thinking-8bit
from JetBrains/Mellum2-12B-A2.5B-Thinking
Params
12B
Weights
≈ 12.9 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-08-11
Qwen2.5-7B-Instruct-1M-abliterated-8bit
from huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-02-19
Qwen3-4B-Instruct-2507-5bit-g32
from Qwen/Qwen3-4B-Instruct-2507
Params
4.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-11
Solar-Open-100B-4bit
from upstage/Solar-Open-100B
Params
103B
Weights
≈ 57.8 GB
Mac memory
96 GB+
solar-apache-2.0 · updated 2026-01-06
c4ai-command-r-plus-08-2024-4bit
mlx-community/c4ai-command-r-plus-08-2024-4bit
Params
104B
Weights
≈ 58.4 GB
Mac memory
96 GB+
cc-by-nc-4.0 · updated 2024-08-31