granite-4.0-3b-vision-nvfp4
from ibm-granite/granite-4.0-3b-vision
Params
4.3B
Weights
≈ 3.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-01
Apple silicon
Apple MLX models
5,842 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 2h ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
5,842 builds · page 54 of 98
karakuri-lm-8x7b-instruct-v0.1
from karakuri-ai/karakuri-lm-8x7b-instruct-v0.1
Params
47B
Weights
≈ 93.4 GB
Mac memory
128 GB+
apache-2.0 · updated 2024-10-11
llama3-8b-cpt-sahabatai-v1-instruct-8bit
from GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2026-06-06
llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-4bit
mlx-community/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-4bit
Params
14B
Weights
≈ 7.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-04-30
phi-4-abliterated-2bit
from huihui-ai/phi-4-abliterated
Params
15B
Weights
≈ 4.6 GB
Mac memory
8 GB+
mit · updated 2025-01-09
rinna-llama-3-youko-8b-instruct-8bit
from rinna/llama-3-youko-8b-instruct
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3 · updated 2024-10-23
tasksource-ModernBERT-base-embed-bf16
from answerdotai/ModernBERT-base
Params
149M
Weights
≈ 298 MB
Mac memory
8 GB+
updated 2025-04-02
QwQ-32B-bf16
from Qwen/QwQ-32B
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-03-05
Orchestrator-8B-4bit
from nvidia/Nemotron-Orchestrator-8B
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+
updated 2025-11-29
stablelm-2-12b-chat-4bit
mlx-community/stablelm-2-12b-chat-4bit
Params
12B
Weights
≈ 7.6 GB
Mac memory
16 GB+
other · updated 2024-04-09
llava-llama-3-8b-v1_1-8bit
mlx-community/llava-llama-3-8b-v1_1-8bit
Params
8.4B
Weights
≈ 9.4 GB
Mac memory
16 GB+
updated 2024-05-14
IQuest-Coder-V1-40B-Loop-Instruct-6bit
from IQuestLab/IQuest-Coder-V1-40B-Loop-Instruct
Params
40B
Weights
≈ 32.3 GB
Mac memory
48 GB+
iquestcoder · updated 2026-01-07
Llama-3-70B-Instruct-Gradient-1048k-2bit
mlx-community/Llama-3-70B-Instruct-Gradient-1048k-2bit
Params
71B
Weights
≈ 22.1 GB
Mac memory
32 GB+
llama3 · updated 2024-05-04
Meta-Llama-3-8B-Instruct
mlx-community/Meta-Llama-3-8B-Instruct
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
llama3 · updated 2024-04-26
Qwen1.5-7B-Chat-4bit
mlx-community/Qwen1.5-7B-Chat-4bit
Params
7.7B
Weights
≈ 5.2 GB
Mac memory
8 GB+
tongyi-qianwen · updated 2024-03-07
c4ai-command-r-08-2024-8bit
mlx-community/c4ai-command-r-08-2024-8bit
Params
32B
Weights
≈ 34.3 GB
Mac memory
48 GB+
cc-by-nc-4.0 · updated 2024-08-31
CodeLlama-7b-Instruct-hf-8bit-mlx
from codellama/CodeLlama-7b-Instruct-hf
Params
6.7B
Weights
≈ 7.2 GB
Mac memory
16 GB+
llama2 · updated 2025-04-27
DiscoLM_German_7b_v1-mlx
from DiscoResearch/DiscoLM_German_7b_v1
Params
7.2B
Weights
≈ 14.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-03
LongCat-Flash-Lite-8bit
from meituan-longcat/LongCat-Flash-Lite
Params
69B
Weights
≈ 72.8 GB
Mac memory
96 GB+
mit · updated 2026-01-29
MiniMax-M2.7-nvfp4
from MiniMaxAI/MiniMax-M2.7
Params
229B
Weights
≈ 129 GB
Mac memory
192 GB+
modified-mit · updated 2026-04-12
aya-23-35B-4bit
mlx-community/aya-23-35B-4bit
Params
35B
Weights
≈ 19.7 GB
Mac memory
24 GB+
cc-by-nc-4.0 · updated 2024-05-23
c4ai-command-r7b-12-2024-3bit
from CohereLabs/c4ai-command-r7b-12-2024
Params
8.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+
cc-by-nc-4.0 · updated 2024-12-17
idefics2-8b-chatty-8bit
mlx-community/idefics2-8b-chatty-8bit
Params
8.4B
Weights
≈ 8.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-01-29
mathstral-7B-v0.1-fp16
mlx-community/mathstral-7B-v0.1-fp16
Params
7.2B
Weights
≈ 14.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-07-16
medgemma-4b-it-bf16
from google/medgemma-4b-pt
Params
5.0B
Weights
≈ 9.9 GB
Mac memory
16 GB+
health-ai-developer-foundations · updated 2025-06-09
CodeLlama-13b-hf-8bit-mlx
from codellama/CodeLlama-13b-hf
Params
13B
Weights
≈ 13.8 GB
Mac memory
24 GB+
llama2 · updated 2025-04-27
DialogueSidon-bf16
from sarulab-speech/DialogueSidon
Params
444M
Weights
≈ 888 MB
Mac memory
8 GB+
cc-by-nc-4.0 · updated 2026-09-06
Falcon-H1-Tiny-90M-Instruct-4bit
from tiiuae/Falcon-H1-Tiny-90M-Instruct
Params
91M
Weights
≈ 51 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon3-Mamba-7B-Instruct-4bits
from tiiuae/Falcon3-Mamba-7B-Instruct
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+
falcon-llm-license · updated 2025-02-14
Huihui-gemma-3n-E4B-it-abliterated-lm-6bit
from huihui-ai/Huihui-gemma-3n-E4B-it-abliterated
Params
6.9B
Weights
≈ 5.6 GB
Mac memory
16 GB+
gemma · updated 2025-09-26
IndexTTS-1.5-MLX
from IndexTeam/IndexTTS-1.5
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2026-08-31
Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-2bit
from Qwen/Qwen2.5-1.5B
Params
1.5B
Weights
≈ 483 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-09-24
Josiefied-Qwen2.5-3B-Instruct-abliterated-v1
from Goekdeniz-Guelmez/Josiefied-Qwen2.5-3B-Instruct-abliterated-v1
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-12-20
KwaiCoder-AutoThink-preview-3bit
from Kwaipilot/KwaiCoder-AutoThink-preview
Params
41B
Weights
≈ 17.7 GB
Mac memory
24 GB+
kwaipilot-license · updated 2025-06-09
Llama-3-8b-Cosmopedia-japanese-4bit
mlx-community/Llama-3-8b-Cosmopedia-japanese-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3 · updated 2024-06-12
Llama-3.1-Swallow-8B-Instruct-v0.2-4bit
from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3.1 · updated 2024-11-11
Ministral-3-3B-Base-2512-bf16
from mistralai/Ministral-3-3B-Base-2512
Params
3.8B
Weights
≈ 7.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-07-18
Ministral-3-8B-Instruct-2512-5bit
from mistralai/Ministral-3-8B-Base-2512
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-12-03
OLMo-2-1124-7B-Instruct-6bit
from allenai/OLMo-2-1124-7B-Instruct
Params
7.3B
Weights
≈ 5.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-11-27
Qwen2-VL-7B-Instruct-abliterated-6bit
from Qwen/Qwen2-VL-7B-Instruct
Params
8.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-24
Qwen2.5-7B-Instruct-kowiki-qa-8bit
mlx-community/Qwen2.5-7B-Instruct-kowiki-qa-8bit
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-12-20
SmolLM3-3B-5bit
from HuggingFaceTB/SmolLM3-3B
Params
3.1B
Weights
≈ 2.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-07-08
SmolVLM-Instruct-6bit
from HuggingFaceTB/SmolVLM-Instruct
Params
2.2B
Weights
≈ 2.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-11-29
UI-TARS-7B-DPO-4bit
mlx-community/UI-TARS-7B-DPO-4bit
Params
8.3B
Weights
≈ 5.6 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-03
gemma-3-1b-it-abliterated-6bit
from mlabonne/gemma-3-1b-it-abliterated
Params
1.3B
Weights
≈ 1.1 GB
Mac memory
8 GB+
gemma · updated 2025-03-22
gemma-4-12B-it-qat-assistant-nvfp4
from google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
Params
423M
Weights
≈ 238 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
gemma-4-E2B-it-qat-assistant-nvfp4
from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
Params
78M
Weights
≈ 45 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
gemma2-9b-cpt-sahabatai-v1-instruct-8bit
from GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct
Params
9.2B
Weights
≈ 9.8 GB
Mac memory
16 GB+
gemma · updated 2026-06-04
granite-20b-code-base-4bit
mlx-community/granite-20b-code-base-4bit
Params
20B
Weights
≈ 11.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-05-14
granite-4.1-30b-8bit
from ibm-granite/granite-4.1-30b
Params
29B
Weights
≈ 30.7 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-05-01
llm-jp-3-1.8b-instruct
mlx-community/llm-jp-3-1.8b-instruct
Params
1.9B
Weights
≈ 3.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-09-25
llm-jp-3.1-1.8b-instruct4-8bit
from llm-jp/llm-jp-3.1-1.8b-instruct4
Params
1.9B
Weights
≈ 2.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-06-16
quantized-gemma-7b
mlx-community/quantized-gemma-7b
Params
8.5B
Weights
≈ 32.6 GB
Mac memory
48 GB+
gemma-terms-of-use · updated 2024-02-21
whisper-small-mlx-fp32
mlx-community/whisper-small-mlx-fp32
Params
—
Weights
—
Mac memory
—
updated 2024-03-09
Qwen3-30B-A3B-4bit-DWQ-053125
from Qwen/Qwen3-30B-A3B
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-06-02
LFM2.5-1.2B-Thinking-8bit
from LiquidAI/LFM2.5-1.2B-Thinking
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+
lfm1.0 · updated 2026-08-13
wespeaker-voxceleb-resnet34-LM
from pyannote/wespeaker-voxceleb-resnet34-LM
Params
—
Weights
—
Mac memory
—
mit · updated 2026-01-16
RakutenAI-3.0-MLX-4bit
from Rakuten/RakutenAI-3.0
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-03-31
Saka-14B-4bit
from Sakalti/Saka-14B
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
updated 2025-02-12
Yi-1.5-34B-Chat-4bit
mlx-community/Yi-1.5-34B-Chat-4bit
Params
34B
Weights
≈ 19.3 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-05-13