Olmo-3-1125-32B-8bit
from allenai/Olmo-3-1125-32B
Params
32B
Weights
≈ 34.2 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-11-21
Apple silicon
Apple MLX models
5,842 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 59m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 44 of 49 · clear filters
Olmo-3.1-32B-Think-bf16
from allenai/Olmo-3.1-32B-Think
Params
32B
Weights
≈ 64.5 GB
Mac memory
96 GB+
apache-2.0 · updated 2025-12-24
OrpoLlama-3-8B-8bit
mlx-community/OrpoLlama-3-8B-8bit
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+
other · updated 2024-04-21
Polaris-4B-Preview-8bit
from POLARIS-Project/Polaris-4B-Preview
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-07-03
Qwen2-0.5B-Instruct
mlx-community/Qwen2-0.5B-Instruct
Params
494M
Weights
≈ 988 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-06
Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr5e-9
from Qwen/Qwen3-30B-A3B-Instruct-2507
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-08-02
ReZero-v0.1-llama-3.2-3b-it-grpo-250404-6bit
from Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+
updated 2025-04-16
Swallow-13b-instruct-v0.1-4bit
mlx-community/Swallow-13b-instruct-v0.1-4bit
Params
13B
Weights
≈ 7.7 GB
Mac memory
16 GB+
llama2 · updated 2024-04-27
Swallow-13b-instruct-v0.1-8bit
mlx-community/Swallow-13b-instruct-v0.1-8bit
Params
13B
Weights
≈ 14.2 GB
Mac memory
24 GB+
llama2 · updated 2024-04-27
Swallow-70b-instruct-v0.1-8bit
mlx-community/Swallow-70b-instruct-v0.1-8bit
Params
69B
Weights
≈ 73.8 GB
Mac memory
96 GB+
llama2 · updated 2024-04-27
Swallow-7b-instruct-v0.1-8bit
mlx-community/Swallow-7b-instruct-v0.1-8bit
Params
6.8B
Weights
≈ 7.4 GB
Mac memory
16 GB+
llama2 · updated 2024-04-27
Teuken-7B-instruct-research-v0.4-4bit
from openGPT-X/Teuken-7B-instruct-research-v0.4
Params
7.5B
Weights
≈ 4.2 GB
Mac memory
8 GB+
other · updated 2025-06-03
ether0-bf16
from futurehouse/ether0
Params
24B
Weights
≈ 94.3 GB
Mac memory
128 GB+
apache-2.0 · updated 2025-06-05
gemma-3-1b-pt-6bit
from google/gemma-3-1b-pt
Params
1.3B
Weights
≈ 1.1 GB
Mac memory
8 GB+
gemma · updated 2025-03-12
gemma-3-270m-qat-6bit
from google/gemma-3-270m-qat
Params
436M
Weights
≈ 354 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
lille-130m-instruct-8bit
from mlx-community/lille-130m-instruct-fp16
Params
127M
Weights
≈ 135 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-09-05
nesso-0.4B-agentic-mlx
from mii-llm/nesso-0.4B-agentic
Params
438M
Weights
≈ 1.8 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-05-08
Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-5Bit
from AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16
Params
27B
Weights
≈ 18.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-05-13 · gated
Qwen3-235B-A22B-4bit-DWQ
from mlx-community/Qwen3-235B-A22B-8bit
Params
235B
Weights
≈ 132 GB
Mac memory
192 GB+
apache-2.0 · updated 2025-05-14
Qwen3-235B-A22B-mixed-3-6bit
from Qwen/Qwen3-235B-A22B
Params
235B
Weights
≈ 191 GB
Mac memory
256 GB+
apache-2.0 · updated 2025-05-09
Gemma-SEA-LION-v4-27B-IT-mlx-4bit
from google/gemma-3-27b-it
Params
27B
Weights
≈ 5.3 GB
Mac memory
8 GB+
gemma · updated 2025-09-10
Hermes-2-Theta-Llama-3-8B-4bit
from NousResearch/Hermes-2-Pro-Llama-3-8B
Params
1.3B
Weights
≈ 1.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-14
LFM2-350M-5bit
from LiquidAI/LFM2-350M
Params
354M
Weights
≈ 244 MB
Mac memory
8 GB+
lfm1.0 · updated 2025-07-11
Orchestrator-8B-bf16
from nvidia/Nemotron-Orchestrator-8B
Params
8.2B
Weights
≈ 16.4 GB
Mac memory
24 GB+
updated 2025-11-29
SynLogic-Mix-3-32B-mlx-OptiQ-5bit
from MiniMaxAI/SynLogic-Mix-3-32B
Params
33B
Weights
≈ 22.5 GB
Mac memory
32 GB+
mit · updated 2026-05-17
XortronCriminalComputingConfig-6bit
from darkc0de/XortronCriminalComputingConfig
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-02-19
granite-4.1-30b-6bit
from ibm-granite/granite-4.1-30b
Params
29B
Weights
≈ 23.5 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-05-01
Apriel-1.5-15b-Thinker-bf16
mlx-community/Apriel-1.5-15b-Thinker-bf16
Params
—
Weights
—
Mac memory
—
mit · updated 2025-10-03
EXAONE-Deep-7.8B-3bit
from LGAI-EXAONE/EXAONE-Deep-7.8B
Params
7.8B
Weights
≈ 3.4 GB
Mac memory
8 GB+
exaone · updated 2025-03-18
Falcon-E-3B-Instruct-8bit
from tiiuae/Falcon-E-3B-Instruct
Params
768M
Weights
≈ 820 MB
Mac memory
8 GB+
falcon-llm-license · updated 2025-06-10
Falcon-H1-Tiny-90M-Instruct-bf16
from tiiuae/Falcon-H1-Tiny-90M-Instruct
Params
91M
Weights
≈ 182 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Falcon-H1-Tiny-90M-Instruct-pre-DPO-6bit
from tiiuae/Falcon-H1-Tiny-90M-Instruct-pre-DPO
Params
91M
Weights
≈ 74 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Granite-4.0-350m-gabliterated-6bit
from Goekdeniz-Guelmez/Granite-4.0-350m-gabliterated
Params
352M
Weights
≈ 286 MB
Mac memory
8 GB+
updated 2026-01-23
Huihui-LFM2.5-1.2B-Instruct-abliterated-6bit
from huihui-ai/Huihui-LFM2.5-1.2B-Instruct-abliterated
Params
1.2B
Weights
≈ 951 MB
Mac memory
8 GB+
lfm1.0 · updated 2026-01-26
Hunyuan-7B-Instruct-8bit
from tencent/Hunyuan-7B-Instruct
Params
7.5B
Weights
≈ 8.0 GB
Mac memory
16 GB+
tencent-license · updated 2025-02-08
Hunyuan-7B-Instruct-fp16
from tencent/Hunyuan-7B-Instruct
Params
7.5B
Weights
≈ 15.0 GB
Mac memory
24 GB+
tencent-license · updated 2025-02-08
JOSIE-1.1-4B-Instruct-bfloat16
from Goekdeniz-Guelmez/JOSIE-1.1-4B-Instruct
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
mit · updated 2026-03-09
Josiefied-LFM2.5-1.2B-Instruct-abliterated-8bit
from Goekdeniz-Guelmez/Josiefied-LFM2.5-1.2B-Instruct-abliterated
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+
updated 2026-01-26
Josiefied-Olmo-3-7B-Instruct-abliterated-v1-8bit
from Goekdeniz-Guelmez/Josiefied-Olmo-3-7B-Instruct-abliterated-v1
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+
updated 2025-11-25
Liberated-Qwen1.5-72B-4bit
mlx-community/Liberated-Qwen1.5-72B-4bit
Params
12B
Weights
≈ 11.9 GB
Mac memory
16 GB+
tongyi-qianwen · updated 2024-04-08
Llama-3-Swallow-8B-Instruct-v0.1-4bit
mlx-community/Llama-3-Swallow-8B-Instruct-v0.1-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3 · updated 2024-07-01
LongCat-Flash-Lite-bf16
from meituan-longcat/LongCat-Flash-Lite
Params
69B
Weights
≈ 137 GB
Mac memory
192 GB+
mit · updated 2026-02-02
Mistral-Small-3.1-24B-Instruct-TXT-2503-3bit-AWQ
from anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF
Params
3.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+
mit · updated 2025-05-20
Olmo-3-7B-Think-bfloat16
from allenai/Olmo-3-7B-Think
Params
7.3B
Weights
≈ 14.6 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-11-21
OpenThinker3-7B-4bit
from open-thoughts/OpenThinker3-7B
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-06-05
Polaris-4B-Preview-6bit
from POLARIS-Project/Polaris-4B-Preview
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-07-03
Qwen2-1.5B-4bit
mlx-community/Qwen2-1.5B-4bit
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-06
Qwen3-4B-Thinking-2507-gabliterated-bfloat16
from Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
updated 2026-01-17
Ring-flash-linear-2.0-128k-5bit
from inclusionAI/Ring-flash-linear-2.0-128k
Params
104B
Weights
≈ 71.6 GB
Mac memory
96 GB+
mit · updated 2025-11-07
Ring-flash-linear-2.0-8bit
from inclusionAI/Ring-flash-linear-2.0
Params
104B
Weights
≈ 111 GB
Mac memory
128 GB+
mit · updated 2025-11-03
SOLAR-10.7b-Instruct-dpo-4bit-mlx
mlx-community/SOLAR-10.7b-Instruct-dpo-4bit-mlx
Params
—
Weights
—
Mac memory
—
cc-by-nc-4.0 · updated 2024-01-26
SeQwential-14B-v1-4bit
from CultriX/SeQwential-14B-v1
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
updated 2024-12-18
UIGEN-T2-7B-mlx-4Bit
from Tesslate/UIGEN-T2-7B
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-05-12
granite-3.2-8b-instruct-preview-8bit
from ibm-granite/granite-3.2-8b-instruct-preview
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-02-08
granite-4.0-h-350m-base-3bit
from ibm-granite/granite-4.0-h-350m-base
Params
340M
Weights
≈ 149 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-28
rnj-1-instruct-6bit
from EssentialAI/rnj-1-instruct
Params
8.3B
Weights
≈ 6.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-12-08
rnj-1-instruct-bfloat16
from EssentialAI/rnj-1-instruct
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-12-08
simplescaling-s1.1-32B-6bit
from simplescaling/s1.1-32B
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-02-16
qwq-bakeneko-32b-8bit
from rinna/qwq-bakeneko-32b
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2025-03-13
dots.llm1.inst-mixed-4-6bit
from dots-studio/dots.llm1.inst
Params
143B
Weights
≈ 116 GB
Mac memory
192 GB+
mit · updated 2025-07-03