LFM2-2.6B-Transcript-8bit
from LiquidAI/LFM2-2.6B-Transcript
Params
2.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+
lfm1.0 · updated 2026-01-07
Apple silicon
Apple MLX models
5,841 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
2,922 builds · page 31 of 49 · clear filters
LFM2.5-1.2B-Instruct-6bit
from LiquidAI/LFM2.5-1.2B-Instruct
Params
1.2B
Weights
≈ 951 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-08-13
Ling-mini-2.0-8bit
from inclusionAI/Ling-mini-2.0
Params
16B
Weights
≈ 17.3 GB
Mac memory
24 GB+
mit · updated 2025-09-11
Llama-3.1-Swallow-8B-Instruct-v0.2-8bit
from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
llama3.1 · updated 2024-11-11
Llama-3.1-Tulu-3-8B-3bit
from allenai/Llama-3.1-Tulu-3-8B
Params
8.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+
llama3.1 · updated 2024-11-25
Magicoder-S-DS-6.7B-4bit-mlx
mlx-community/Magicoder-S-DS-6.7B-4bit-mlx
Params
—
Weights
—
Mac memory
—
deepseek · updated 2024-01-14
Megrez-3B-Instruct-abliterated-6bit
from huihui-ai/Megrez-3B-Instruct-abliterated
Params
2.9B
Weights
≈ 2.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-02-26
MiniMax-M2-REAP-139B-A10B-mxfp4
from cerebras/MiniMax-M2-REAP-139B-A10B
Params
139B
Weights
≈ 78.3 GB
Mac memory
96 GB+
other · updated 2026-01-03
Phi-4-reasoning-plus-6bit
from microsoft/Phi-4-reasoning-plus
Params
15B
Weights
≈ 11.9 GB
Mac memory
16 GB+
mit · updated 2025-05-17
Seed-Coder-8B-Reasoning-bf16-mlx-4Bit
from ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16
Params
8.3B
Weights
≈ 4.6 GB
Mac memory
8 GB+
mit · updated 2025-07-18
Snorkel-Mistral-PairRM-DPO-4bit-mlx
mlx-community/Snorkel-Mistral-PairRM-DPO-4bit-mlx
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2024-01-26
Trinity-Nano-Preview-4bit
from arcee-ai/Trinity-Nano-Preview
Params
6.1B
Weights
≈ 3.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-12-03
falcon-mamba-7b-8bit-instruct
from tiiuae/falcon-mamba-7b-instruct
Params
7.3B
Weights
≈ 7.7 GB
Mac memory
16 GB+
falcon-mamba-7b-license · updated 2024-11-15
granite-4.0-h-tiny-8bit
from ibm-granite/granite-4.0-h-tiny
Params
6.9B
Weights
≈ 7.4 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-10-02
simplescaling-s1.1-32B-fp32
from simplescaling/s1.1-32B
Params
33B
Weights
≈ 131 GB
Mac memory
192 GB+
apache-2.0 · updated 2025-02-16
Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-4Bit
from AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16
Params
27B
Weights
≈ 15.1 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-05-13 · gated
Llama-3-8B-Instruct-Gradient-1048k-4bit
mlx-community/Llama-3-8B-Instruct-Gradient-1048k-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3 · updated 2024-05-05
MiroThinker-1.7-mini-mlx-4Bit
from miromind-ai/MiroThinker-1.7-mini
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-03-15
L3.3-MS-Nevoria-70b-4bit
from EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
Params
11B
Weights
≈ 9.4 GB
Mac memory
16 GB+
eva-llama3.3 · updated 2025-02-22
LFM2-700M-6bit
from LiquidAI/LFM2-700M
Params
742M
Weights
≈ 603 MB
Mac memory
8 GB+
lfm1.0 · updated 2025-07-11
LFM2.5-350M-bf16
from LiquidAI/LFM2.5-350M
Params
354M
Weights
≈ 709 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-08-13
Nemotron-Cascade-2-30B-A3B-5bit
from nvidia/Nemotron-Cascade-2-30B-A3B
Params
32B
Weights
≈ 21.7 GB
Mac memory
32 GB+
nvidia-open-model-license · updated 2026-03-20
Phi-4-reasoning-plus-bf16
from microsoft/Phi-4-reasoning-plus
Params
15B
Weights
≈ 29.3 GB
Mac memory
48 GB+
mit · updated 2025-05-01
Qwen1.5-110B-Chat-8bit
mlx-community/Qwen1.5-110B-Chat-8bit
Params
111B
Weights
≈ 118 GB
Mac memory
192 GB+
tongyi-qianwen · updated 2024-04-26
Qwen1.5-32B-Chat-8bit
mlx-community/Qwen1.5-32B-Chat-8bit
Params
33B
Weights
≈ 35.3 GB
Mac memory
48 GB+
tongyi-qianwen · updated 2024-04-05
Qwen3-235B-A22B-3bit
from Qwen/Qwen3-235B-A22B
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+
apache-2.0 · updated 2025-05-01
Qwen3-Next-80B-A3B-Thinking-5bit
from Qwen/Qwen3-Next-80B-A3B-Thinking
Params
80B
Weights
≈ 54.8 GB
Mac memory
64 GB+
apache-2.0 · updated 2025-09-13
Swallow-70b-instruct-v0.1-4bit
mlx-community/Swallow-70b-instruct-v0.1-4bit
Params
69B
Weights
≈ 39.4 GB
Mac memory
48 GB+
llama2 · updated 2024-04-26
gemma-2-9b-fp16
mlx-community/gemma-2-9b-fp16
Params
9.2B
Weights
≈ 18.5 GB
Mac memory
24 GB+
gemma · updated 2024-06-27
gemma-3-270m-it-4bit-DWQ
from google/gemma-3-270m-it
Params
268M
Weights
≈ 151 MB
Mac memory
8 GB+
gemma · updated 2025-08-16
granite-4.0-1b-base-4bit
from ibm-granite/granite-4.0-1b-base
Params
1.6B
Weights
≈ 918 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
rho-math-1b-interpreter-v0.1-4bit
mlx-community/rho-math-1b-interpreter-v0.1-4bit
Params
1.1B
Weights
≈ 713 MB
Mac memory
8 GB+
mit · updated 2024-04-15
rho-math-1b-v0.1-4bit
mlx-community/rho-math-1b-v0.1-4bit
Params
1.1B
Weights
≈ 713 MB
Mac memory
8 GB+
mit · updated 2024-04-12
stable-code-3b-mlx
mlx-community/stable-code-3b-mlx
Params
—
Weights
—
Mac memory
—
other · updated 2024-01-17
xLAM-7b-fc-r
from Salesforce/xLAM-7b-fc-r
Params
6.9B
Weights
≈ 13.8 GB
Mac memory
24 GB+
cc-by-nc-4.0 · updated 2024-10-22
Dans-PersonalityEngine-V1.2.0-24b-mlx-4Bit
from PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-28
EXAONE-4.0-32B-bf16
from LGAI-EXAONE/EXAONE-4.0-32B
Params
32B
Weights
≈ 64.0 GB
Mac memory
96 GB+
exaone · updated 2025-07-15
Falcon-H1-0.5B-Instruct-5bit
from tiiuae/Falcon-H1-0.5B-Instruct
Params
521M
Weights
≈ 359 MB
Mac memory
8 GB+
falcon-llm-license · updated 2025-09-26
Falcon-H1-Tiny-90M-Instruct-pre-DPO-4bit
from tiiuae/Falcon-H1-Tiny-90M-Instruct-pre-DPO
Params
91M
Weights
≈ 51 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Hermes-4-70B-6bit
from NousResearch/Hermes-4-70B
Params
71B
Weights
≈ 57.3 GB
Mac memory
96 GB+
llama3 · updated 2025-08-26
Hunyuan-7B-Instruct-4bit
from tencent/Hunyuan-7B-Instruct
Params
7.5B
Weights
≈ 4.2 GB
Mac memory
8 GB+
tencent-license · updated 2025-02-08
Jan-nano-4B-bf16
from Menlo/Jan-nano
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-07-05
Ling-mini-2.0-2bit
from inclusionAI/Ling-mini-2.0
Params
16B
Weights
≈ 5.1 GB
Mac memory
8 GB+
mit · updated 2025-09-21
Llama3-8B-Medicine-4bit
from instruction-pretrain/medicine-Llama3-8B
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3 · updated 2025-06-19
MiniCPM3-4B-8bit
from Goekdeniz-Guelmez/OpenBNB-MiniCPM3-4b
Params
4.3B
Weights
≈ 4.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-03-19
OLMoE-1B-7B-0125
from allenai/OLMoE-1B-7B-0125
Params
6.9B
Weights
≈ 13.8 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-16
Phi-3-medium-128k-instruct-bf16
mlx-community/Phi-3-medium-128k-instruct-bf16
Params
14B
Weights
≈ 27.9 GB
Mac memory
48 GB+
mit · updated 2024-09-02
QwQ-coder-32B-4bit
from YOYO-AI/QwQ-coder-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
updated 2025-04-21
Qwen2.5-14B-bf16
mlx-community/Qwen2.5-14B-bf16
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+
apache-2.0 · updated 2024-09-18
Rombos-LLM-V2.6-Qwen-14b-4bit
from rombodawg/Rombos-LLM-V2.6-Qwen-14b
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-10-21
granite-4.0-350m-3bit
from ibm-granite/granite-4.0-350m
Params
352M
Weights
≈ 154 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
granite-4.0-h-small-8bit
from ibm-granite/granite-4.0-h-small
Params
32B
Weights
≈ 34.2 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-10-02
helium-1-preview-2b
from kyutai/helium-1-preview-2b
Params
2.2B
Weights
≈ 4.3 GB
Mac memory
8 GB+
cc-by-4.0 · updated 2025-01-18
llm-jp-3-8x1.8b-instruct3-8bit
from llm-jp/llm-jp-3-8x1.8b-instruct3
Params
9.3B
Weights
≈ 9.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-27
mistral-7b-v0.1-GreeceRome-v0.1
mlx-community/mistral-7b-v0.1-GreeceRome-v0.1
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2024-01-14
phi-2-super-4bit
mlx-community/phi-2-super-4bit
Params
2.8B
Weights
≈ 1.8 GB
Mac memory
8 GB+
mit · updated 2024-03-02
Qwen3-235B-A22B-Thinking-2507-3bit-DWQ
from Qwen/Qwen3-235B-A22B-Thinking-2507
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+
apache-2.0 · updated 2025-07-26
Llama-3-8B-Instruct-262k-4bit
mlx-community/Llama-3-8B-Instruct-262k-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3 · updated 2024-05-05
LFM2-8B-A1B-fp16
from LiquidAI/LFM2-8B-A1B
Params
8.3B
Weights
≈ 33.4 GB
Mac memory
48 GB+
lfm1.0 · updated 2025-10-07
IQuest-Coder-V1-40B-Thinking-8bit
mlx-community/IQuest-Coder-V1-40B-Thinking-8bit
Params
40B
Weights
≈ 42.3 GB
Mac memory
64 GB+
updated 2026-03-31