gemma-4-E4B-it-qat-assistant-6bit
from google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant
Params
79M
Weights
≈ 65 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
Apple silicon
Apple MLX models
5,842 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 6m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 38 of 49 · clear filters
helium-1-preview-2b-float32
from kyutai/helium-1-preview-2b
Params
2.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+
cc-by-4.0 · updated 2025-01-18
llm-jp-3-1.8b-instruct3-4bit
from llm-jp/llm-jp-3-1.8b-instruct3
Params
1.9B
Weights
≈ 1.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-02-07
sarashina2.2-3b-instruct-v0.1
from sbintuitions/sarashina2.2-3b-instruct-v0.1
Params
3.4B
Weights
≈ 6.7 GB
Mac memory
16 GB+
mit · updated 2025-06-30
MiroThinker-v1.5-30B
from miromind-ai/MiroThinker-v1.5-30B
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+
mit · updated 2026-01-24
miscii-14b-1028-4bit
from sthenno-com/miscii-14b-1028
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-11-14
FastContext-1.0-4B-SFT-8bit
from ShaunGves/FastContext-1.0-4B-SFT
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
mit · updated 2026-07-08
LFM2-2.6B-Exp-8bit
from LiquidAI/LFM2-2.6B-Exp
Params
2.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+
lfm1.0 · updated 2025-12-26
SWE-agent-LM-32B-4bit
from SWE-bench/SWE-agent-LM-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-05-12
DeepScaleR-1.5B-Preview-Q8
from agentica-org/DeepScaleR-1.5B-Preview
Params
1.8B
Weights
≈ 1.9 GB
Mac memory
8 GB+
mit · updated 2025-02-20
LLaDA2.0-mini-preview-4bit
from inclusionAI/LLaDA2.0-mini-preview
Params
16B
Weights
≈ 9.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-10-18
LongCat-Flash-Chat-4bit
from meituan-longcat/LongCat-Flash-Chat
Params
561B
Weights
≈ 315 GB
Mac memory
512 GB+
mit · updated 2025-09-04
Ring-mini-2.0-6bit
from inclusionAI/Ring-mini-2.0
Params
16B
Weights
≈ 13.2 GB
Mac memory
24 GB+
mit · updated 2025-09-15
SmolLM-1.7B-4bit
mlx-community/SmolLM-1.7B-4bit
Params
1.7B
Weights
≈ 963 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-07-16
SmolLM-1.7B-fp16
mlx-community/SmolLM-1.7B-fp16
Params
1.7B
Weights
≈ 3.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-07-16
c4ai-command-a-03-2025-3bit
from CohereLabs/c4ai-command-a-03-2025
Params
111B
Weights
≈ 48.6 GB
Mac memory
64 GB+
cc-by-nc-4.0 · updated 2025-03-18
miscii-14b-0218-8bit
from sthenno-com/miscii-14b-0218
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-10
rnj-1-instruct-8bit
from EssentialAI/rnj-1-instruct
Params
8.3B
Weights
≈ 8.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-12-08
sarvam-m-mlx-3Bit
from sarvamai/sarvam-m
Params
24B
Weights
≈ 10.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-05-31
Anubis-70B-v1.1-bf16
from TheDrummer/Anubis-70B-v1.1
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+
updated 2025-06-28
DeepCoder-14B-Preview-bf16
from agentica-org/DeepCoder-14B-Preview
Params
15B
Weights
≈ 29.5 GB
Mac memory
48 GB+
mit · updated 2025-04-08
EXAONE-Deep-7.8B-bf16
from LGAI-EXAONE/EXAONE-Deep-7.8B
Params
7.8B
Weights
≈ 15.6 GB
Mac memory
24 GB+
exaone · updated 2025-03-18
Falcon-H1-0.5B-Instruct-8bit
from tiiuae/Falcon-H1-0.5B-Instruct
Params
521M
Weights
≈ 554 MB
Mac memory
8 GB+
falcon-llm-license · updated 2025-09-26
Falcon-H1-Tiny-90M-Instruct-Curriculum-4bit
from tiiuae/Falcon-H1-Tiny-90M-Instruct-Curriculum
Params
91M
Weights
≈ 51 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon3-10B-Instruct-abliterated-8bit
from huihui-ai/Falcon3-10B-Instruct-abliterated
Params
10B
Weights
≈ 10.9 GB
Mac memory
16 GB+
falcon-llm-license · updated 2025-02-19
Falcon3-7B-Instruct-1.58bit-8bit
from tiiuae/Falcon3-7B-Instruct-1.58bit
Params
1.9B
Weights
≈ 2.5 GB
Mac memory
8 GB+
falcon-llm-license · updated 2025-06-10
IQuest-Coder-V1-14B-Base-Stage1-8bit
mlx-community/IQuest-Coder-V1-14B-Base-Stage1-8bit
Params
14B
Weights
≈ 15.3 GB
Mac memory
24 GB+
updated 2026-03-25
Josiefied-Qwen3-0.6B-abliterated-v1-float32
from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v1
Params
596M
Weights
≈ 2.4 GB
Mac memory
8 GB+
updated 2025-05-05
LFM2-2.6B-Transcript-6bit
from LiquidAI/LFM2-2.6B-Transcript
Params
2.6B
Weights
≈ 2.1 GB
Mac memory
8 GB+
lfm1.0 · updated 2026-01-07
LFM2.5-1.2B-Instruct-5bit
from LiquidAI/LFM2.5-1.2B-Instruct
Params
1.2B
Weights
≈ 805 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-08-13
LFM2.5-1.2B-Thinking-5bit
from LiquidAI/LFM2.5-1.2B-Thinking
Params
1.2B
Weights
≈ 805 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-08-13
Laguna-M.1-6bit
from poolside/Laguna-M.1
Params
226B
Weights
≈ 183 GB
Mac memory
256 GB+
apache-2.0 · updated 2026-06-18
Laguna-XS.2-mxfp4
from poolside/Laguna-XS.2
Params
33B
Weights
≈ 18.8 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-04-28
Llama-3-Swallow-70B-Instruct-v0.1-8bit
mlx-community/Llama-3-Swallow-70B-Instruct-v0.1-8bit
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+
llama3 · updated 2024-07-01
Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct-bf16
from nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+
cc-by-nc-4.0 · updated 2025-06-30
Llama3-ChatQA-1.5-8B-4bit
mlx-community/Llama3-ChatQA-1.5-8B-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3 · updated 2024-05-02
Nanbeige4-3B-Thinking-2511-gabliterated-4bit
from Goekdeniz-Guelmez/Nanbeige4-3B-Thinking-2511-gabliterated
Params
3.9B
Weights
≈ 2.2 GB
Mac memory
8 GB+
updated 2026-01-13
Olmo-3-7B-Think-SFT-4bit
from allenai/Olmo-3-7B-Think-SFT
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-11-21
OpenMath-Nemotron-14B-4bit
from nvidia/OpenMath-Nemotron-14B
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
cc-by-4.0 · updated 2025-04-25
OrpoLlama-3-8B-4bit
mlx-community/OrpoLlama-3-8B-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
other · updated 2024-04-21
Ouro-1.4B-Thinking-4bit
from ByteDance/Ouro-1.4B-Thinking
Params
1.4B
Weights
≈ 807 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-11-28
Preferred-MedLLM-Qwen-72B-4bit
from pfnet/Preferred-MedLLM-Qwen-72B
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+
qwen · updated 2025-03-08
QwQ-0.5B-6bit
from InfiniAILab/QwQ-0.5B
Params
494M
Weights
≈ 401 MB
Mac memory
8 GB+
updated 2025-04-07
Qwen2-Math-1.5B-Instruct-4bit
mlx-community/Qwen2-Math-1.5B-Instruct-4bit
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-08-09
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr5e-8
from Qwen/Qwen3-30B-A3B-Instruct-2507
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-07-31
Qwen3-4B-Thinking-2507-6bit
from Qwen/Qwen3-4B-Thinking-2507
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-08-06
Singlish-TinyLlama-v0.1
mlx-community/Singlish-TinyLlama-v0.1
Params
—
Weights
—
Mac memory
—
cc-by-nc-sa-4.0 · updated 2024-01-14
SmolLM3-3B-Base-6bit
from HuggingFaceTB/SmolLM3-3B-Base
Params
3.1B
Weights
≈ 2.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-07-08
TeleChat3-36B-Thinking-8bit
from Tele-AI/TeleChat3-36B-Thinking
Params
36B
Weights
≈ 38.5 GB
Mac memory
48 GB+
updated 2026-01-19
Tessa-T1-7B-mlx-bf16
from Tesslate/Tessa-T1-7B
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-03-25
gemma-3-270m-it-5bit
from google/gemma-3-270m-it
Params
436M
Weights
≈ 300 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
gemma-4-E2B-it-qat-assistant-mxfp8
from google/gemma-4-E2B-it-qat-q4_0-unquantized-assistant
Params
78M
Weights
≈ 84 MB
Mac memory
8 GB+
gemma · updated 2026-06-05
granite-4.0-350m-base-4bit
from ibm-granite/granite-4.0-350m-base
Params
352M
Weights
≈ 198 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
granite-4.0-h-1b-base-4bit
from ibm-granite/granite-4.0-h-1b-base
Params
1.5B
Weights
≈ 823 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
granite-4.1-3b-5bit
from ibm-granite/granite-4.1-3b
Params
3.4B
Weights
≈ 2.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-05-01
openchat-3.6-8b-20240522-2bit
from meta-llama/Meta-Llama-3-8B
Params
753M
Weights
≈ 659 MB
Mac memory
8 GB+
llama3 · updated 2024-05-24
phi-1_5
mlx-community/phi-1_5
Params
1.4B
Weights
≈ 2.8 GB
Mac memory
8 GB+
mit · updated 2024-07-25
sarashina2.2-1b-instruct-v0.1
from sbintuitions/sarashina2.2-1b-instruct-v0.1
Params
1.4B
Weights
≈ 2.8 GB
Mac memory
8 GB+
mit · updated 2025-06-27
simplescaling-s1-32B-8bit
from simplescaling/s1-32B
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-02-11
tempesthenno-reasoning-exp-1216-mlx-4Bit
from sthenno/tempesthenno-reasoning-exp-1216
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
updated 2025-12-17