granite-4.0-micro-8bit
from ibm-granite/granite-4.0-micro
Params
3.4B
Weights
≈ 3.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-02
Apple silicon
Apple MLX models
5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 32m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 21 of 49 · clear filters
llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
mlx-community/llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0
Params
14B
Weights
≈ 27.4 GB
Mac memory
48 GB+
apache-2.0 · updated 2024-04-30
MiniMax-M2-8bit
from MiniMaxAI/MiniMax-M2
Params
229B
Weights
≈ 243 GB
Mac memory
512 GB+
mit · updated 2025-10-28
Ouro-2.6B-Thinking-4bit
from ByteDance/Ouro-2.6B-Thinking
Params
2.7B
Weights
≈ 1.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-11-28
LongWriter-llama3.1-8b-6bit
from zai-org/LongWriter-llama3.1-8b
Params
8.0B
Weights
≈ 6.5 GB
Mac memory
16 GB+
llama3.1 · updated 2025-09-28
granite-4.0-h-micro-8bit
from ibm-granite/granite-4.0-h-micro
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-02
Apertus-8B-Instruct-2509-8bit
from swiss-ai/Apertus-8B-Instruct-2509
Params
8.1B
Weights
≈ 8.6 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-09-03
Qwen3-30B-A3B-Instruct-2507-4bit-ODWQ
from Qwen/Qwen3-30B-A3B
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-08-16
Qwen2.5-0.5B-Instruct-2bit-mlx
from Qwen/Qwen2.5-0.5B-Instruct
Params
494M
Weights
≈ 155 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-02-17
kanana-2-3b-instruct-8bit
from kakaocorp/kanana-2-3b-instruct
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+
kanana-open-license · updated 2026-08-06
granite-4.1-30b-mxfp8
from ibm-granite/granite-4.1-30b
Params
29B
Weights
≈ 30.7 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-04-30
DeepSeek-V3.1-Terminus-4bit
from deepseek-ai/DeepSeek-V3.1-Terminus
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+
mit · updated 2025-09-22
Ornith-1.0-9B-8bit
from ornith-ai/Ornith-1.0-9B
Params
9.4B
Weights
≈ 10.4 GB
Mac memory
16 GB+
mit · updated 2026-06-28
Stockmark-2-100B-Instruct-beta-4bit
from stockmark/Stockmark-2-100B-Instruct-beta
Params
96B
Weights
≈ 54.0 GB
Mac memory
64 GB+
mit · updated 2025-03-08
ABEJA-Qwen3-14B-Agentic-256k-v0.1-MLX-8bit
from abeja/ABEJA-Qwen3-14B-Agentic-256k-v0.1
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-03-28
DeepSeek-R1-0528-3bit
from deepseek-ai/DeepSeek-R1-0528
Params
671B
Weights
≈ 294 GB
Mac memory
512 GB+
mit · updated 2025-05-29
Falcon-H1-Tiny-Coder-90M-4bit
from tiiuae/Falcon-H1-Tiny-Coder-90M
Params
91M
Weights
≈ 51 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Josiefied-Qwen3-0.6B-abliterated-v1-4bit
from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v1
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+
updated 2025-04-29
Qwen3-30B-A3B-Instruct-2507-6bit
from Qwen/Qwen3-30B-A3B-Instruct-2507
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-07-29
llm-jp-3-13b-instruct3
from llm-jp/llm-jp-3-13b-instruct3
Params
14B
Weights
≈ 27.4 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-02-05
magnum-v4-123b-4bit
from anthracite-org/magnum-v4-123b
Params
123B
Weights
≈ 69.0 GB
Mac memory
96 GB+
mrl · updated 2024-12-18
GLM-4.5-Air-6bit
from zai-org/GLM-4.5-Air
Params
107B
Weights
≈ 86.8 GB
Mac memory
128 GB+
mit · updated 2025-07-28
dhara-250m-OptiQ-8bit
from codelion/dhara-250m
Params
249M
Weights
≈ 356 MB
Mac memory
8 GB+
apache-2.0 · updated 2026-07-12
Mellum-4b-base
from JetBrains/Mellum-4b-base
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-06-28
Kimi-Linear-48B-A3B-Instruct-mlx-bf16
from moonshotai/Kimi-Linear-48B-A3B-Instruct
Params
49B
Weights
≈ 98.2 GB
Mac memory
128 GB+
mit · updated 2026-01-22
MiniCPM4-8B-4bit
from openbmb/MiniCPM4-8B
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-06-09
Mistral-7B-Instruct-v0.1-4bit-mlx
mlx-community/Mistral-7B-Instruct-v0.1-4bit-mlx
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2024-01-04
Phi-4-mini-reasoning-6bit
from microsoft/Phi-4-mini-reasoning
Params
3.8B
Weights
≈ 3.1 GB
Mac memory
8 GB+
mit · updated 2025-05-01
gemma-2-9b-it-6bit
from google/gemma-2-9b-it
Params
9.2B
Weights
≈ 7.5 GB
Mac memory
16 GB+
gemma · updated 2025-03-06
DeepSeek-V4-Flash-5bit
mlx-community/DeepSeek-V4-Flash-5bit
Params
284B
Weights
≈ 196 GB
Mac memory
256 GB+
updated 2026-04-25
Llama-3-ELYZA-JP-8B-8bit
mlx-community/Llama-3-ELYZA-JP-8B-8bit
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2024-06-26
Nex-N2.5-mini-oQ4
from nex-agi/Nex-N2.5-mini
Params
35B
Weights
≈ 19.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-09-11
Phi-4-reasoning-4bit
from microsoft/Phi-4-reasoning
Params
15B
Weights
≈ 8.2 GB
Mac memory
16 GB+
mit · updated 2025-05-01
distilgpt2
from distilbert/distilgpt2
Params
82M
Weights
≈ 164 MB
Mac memory
8 GB+
apache-2.0 · updated 2026-06-27
Hunyuan-A52B-Instruct-3bit
from tencent-community/Hunyuan-A52B-Instruct
Params
389B
Weights
≈ 170 GB
Mac memory
256 GB+
updated 2024-11-23
Phi-3-vision-128k-instruct-8bit
mlx-community/Phi-3-vision-128k-instruct-8bit
Params
4.1B
Weights
≈ 4.4 GB
Mac memory
8 GB+
mit · updated 2024-06-24
codegemma-1.1-2b-8bit
from google/codegemma-1.1-2b
Params
2.5B
Weights
≈ 2.7 GB
Mac memory
8 GB+
gemma · updated 2025-06-02
meta-llama-Llama-4-Scout-17B-16E-fp16
from meta-llama/Llama-4-Scout-17B-16E
Params
108B
Weights
≈ 216 GB
Mac memory
256 GB+
llama4 · updated 2025-04-06
Meta-Llama-3.1-70B-4bit
mlx-community/Meta-Llama-3.1-70B-4bit
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+
llama3.1 · updated 2024-07-23
Qwen3-30B-A3B-Instruct-2507-5bit
from Qwen/Qwen3-30B-A3B-Instruct-2507
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-07-29
gemma-4-31B-it-qat-assistant-mxfp8
from google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
Params
470M
Weights
≈ 499 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
Bio-Medical-Llama-3-8B
from ContactDoctor/Bio-Medical-Llama-3-8B
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
other · updated 2025-01-26
Ring-mini-2.0-4bit
from inclusionAI/Ring-mini-2.0
Params
16B
Weights
≈ 9.1 GB
Mac memory
16 GB+
mit · updated 2025-09-15
granite-8b-code-instruct-8bit
from ibm-granite/granite-8b-code-base-4k
Params
8.1B
Weights
≈ 8.6 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-05-06
Mistral7B-PairRM-SPPO-Iter3-unquantized
mlx-community/Mistral7B-PairRM-SPPO-Iter3-unquantized
Params
7.2B
Weights
≈ 14.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-05-07
c4ai-command-a-03-2025-bf16
from CohereLabs/c4ai-command-a-03-2025
Params
111B
Weights
≈ 222 GB
Mac memory
256 GB+
cc-by-nc-4.0 · updated 2025-03-18
DeepSeek-V4-Flash-nvfp4
mlx-community/DeepSeek-V4-Flash-nvfp4
Params
284B
Weights
≈ 160 GB
Mac memory
192 GB+
updated 2026-04-25
Phi-3.5-MoE-instruct-bf16
mlx-community/Phi-3.5-MoE-instruct-bf16
Params
42B
Weights
≈ 83.7 GB
Mac memory
96 GB+
mit · updated 2024-08-24
Qwen-3-32B-Medical-Reasoning-4bit
from nicoboss/Qwen-3-32B-Medical-Reasoning
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-06-03
Qwen2.5-32B-Instruct-bf16
from Qwen/Qwen2.5-32B
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2024-09-18
Qwen3-Coder-REAP-25B-A3B-mlx-8Bit
from cerebras/Qwen3-Coder-REAP-25B-A3B
Params
25B
Weights
≈ 26.4 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-11-05
SmolLM-360M-4bit
mlx-community/SmolLM-360M-4bit
Params
362M
Weights
≈ 204 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-07-16
gemma2-9b-cpt-sahabatai-v1-instruct-4bit
from GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
Params
9.2B
Weights
≈ 5.2 GB
Mac memory
8 GB+
gemma · updated 2026-06-03
granite-4.0-h-350m-5bit
from ibm-granite/granite-4.0-h-350m
Params
340M
Weights
≈ 234 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
granite-8b-code-instruct-4bit
from ibm-granite/granite-8b-code-base-4k
Params
8.1B
Weights
≈ 4.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-05-06
Meta-Llama-3-8B-Instruct-8bit
mlx-community/Meta-Llama-3-8B-Instruct-8bit
Params
8.0B
Weights
≈ 9.0 GB
Mac memory
16 GB+
llama3 · updated 2024-04-19
Phi-3-medium-128k-instruct-4bit
mlx-community/Phi-3-medium-128k-instruct-4bit
Params
14B
Weights
≈ 7.9 GB
Mac memory
16 GB+
mit · updated 2024-07-11
mistral-7b-instruct-v0.1-4bit-ngs
mlx-community/mistral-7b-instruct-v0.1-4bit-ngs
Params
7.2B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-02-09
AREX-Turbo-8bit
from BAAI/AREX-Turbo
Params
4.5B
Weights
≈ 5.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-07-28
Apertus-8B-2509-4bit
from swiss-ai/Apertus-8B-2509
Params
8.1B
Weights
≈ 4.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-09-03