Apple MLX models

dolphin-2.9.3-qwen2-1.5b-4bit

from Qwen/Qwen2-1.5B

4-bit

Uncategorised · Qwen ↓ 39 · ♥ 1

Params

241M

Weights

≈ 205 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-06-14

dolphin-2_6-phi-2-mlx

mlx-community/dolphin-2_6-phi-2-mlx

Uncategorised ↓ 39 · ♥ 1

Params

—

Weights

—

Mac memory

—

mit · updated 2024-01-08

gemma-4-E4B-it-qat-nvfp4

from google/gemma-4-e4b-it-qat-q4_0-unquantized

4-bit

Any to any · Google · Gemma ↓ 39 · ♥ 1

Params

7.9B

Weights

≈ 5.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-06-05

grug-27b-Text-mlx-8Bit

from ProCreations/grug-27b

8-bit

Text generation · ProCreations ↓ 39 · ♥ 1

Params

27B

Weights

≈ 28.6 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-07-23

internlm2_5-20b-chat_8bit

mlx-community/internlm2_5-20b-chat_8bit

8-bit

Text generation ↓ 39 · ♥ 1

Params

20B

Weights

≈ 21.1 GB

Mac memory

32 GB+

other · updated 2024-08-22

3b-ko-ft-research_release-4bit

from canopylabs/orpheus-3b-0.1-pretrained

4-bit

Text to speech · canopylabs ↓ 39 · ♥ 0

Params

3.3B

Weights

≈ 1.9 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-09

Cydonia-24B-v3-bf16

from TheDrummer/Cydonia-24B-v3

bf16

Text generation · TheDrummer ↓ 39 · ♥ 0

Params

24B

Weights

≈ 47.1 GB

Mac memory

64 GB+

other · updated 2025-06-04

Falcon-H1-Tiny-90M-Base-4bit

from tiiuae/Falcon-H1-Tiny-90M-Base

4-bit

Text generation · TII · Falcon ↓ 39 · ♥ 0

Params

91M

Weights

≈ 51 MB

Mac memory

8 GB+

falcon-llm-license · updated 2026-01-28

Falcon-H1-Tiny-R-0.6B-4bit

from tiiuae/Falcon-H1-Tiny-R-0.6B

4-bit

Text generation · TII · Falcon ↓ 39 · ♥ 0

Params

622M

Weights

≈ 351 MB

Mac memory

8 GB+

falcon-llm-license · updated 2026-01-28

Falcon3-7B-Instruct-1.58bit

from tiiuae/Falcon3-7B-Instruct-1.58bit

58-bit

Text generation · TII · Falcon ↓ 39 · ♥ 0

Params

2.5B

Weights

≈ 3.3 GB

Mac memory

8 GB+

falcon-llm-license · updated 2025-06-10

INTELLECT-1-Instruct-8bit

from PrimeIntellect/INTELLECT-1-Instruct

8-bit

Text generation · PrimeIntellect ↓ 39 · ♥ 0

Params

10B

Weights

≈ 10.8 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-11-30

IQuest-Coder-V1-14B-Instruct-8bit

mlx-community/IQuest-Coder-V1-14B-Instruct-8bit

8-bit

Text generation ↓ 39 · ♥ 0

Params

14B

Weights

≈ 15.3 GB

Mac memory

24 GB+

updated 2026-03-31

Llama-3_3-Nemotron-Super-49B-v1-mlx-6bit

from nvidia/Llama-3_3-Nemotron-Super-49B-v1

6-bit

Text generation · NVIDIA ↓ 39 · ♥ 0

Params

50B

Weights

≈ 40.5 GB

Mac memory

48 GB+

nvidia-open-model-license · updated 2025-04-08

Ministral-3-8B-Base-2512-6bit

from mistralai/Ministral-3-8B-Base-2512

6-bit

Vision + text · Mistral ↓ 39 · ♥ 0

Params

8.9B

Weights

≈ 8.4 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-07-18

My-Phi-3-medium-128k-instruct-4bit

mlx-community/My-Phi-3-medium-128k-instruct-4bit

4-bit

Text generation ↓ 39 · ♥ 0

Params

14B

Weights

≈ 7.9 GB

Mac memory

16 GB+

mit · updated 2024-07-08

North-Micro-Vision-Instruct-mxfp8

from CohereLabs/North-Micro-Vision-Instruct

MXFP8

Vision + text · Cohere ↓ 39 · ♥ 0

Params

2.5B

Weights

≈ 3.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-08-12

North-Micro-Vision-Instruct-nvfp4

from CohereLabs/North-Micro-Vision-Instruct

4-bit

Vision + text · Cohere ↓ 39 · ♥ 0

Params

2.5B

Weights

≈ 2.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-08-12

Ouro-1.4B-4bit

from ByteDance/Ouro-1.4B

4-bit

Text generation · ByteDance ↓ 39 · ♥ 0

Params

1.4B

Weights

≈ 807 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-11-09

Ouro-2.6B-4bit

from ByteDance/Ouro-2.6B

4-bit

Text generation · ByteDance ↓ 39 · ♥ 0

Params

2.7B

Weights

≈ 1.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-11-09

Qwen3-30B-A3B-Instruct-2507-bf16

from Qwen/Qwen3-30B-A3B-Instruct-2507

bf16

Text generation · Qwen ↓ 39 · ♥ 0

Params

31B

Weights

≈ 61.1 GB

Mac memory

96 GB+

apache-2.0 · updated 2025-08-01

Qwen3-VL-2B-Instruct-5bit

mlx-community/Qwen3-VL-2B-Instruct-5bit

5-bit

Vision + text ↓ 39 · ♥ 0

Params

2.1B

Weights

≈ 2.0 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-21

Qwen3-VL-32B-Thinking-bf16

mlx-community/Qwen3-VL-32B-Thinking-bf16

bf16

Vision + text ↓ 39 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-10-21

Qwen3.5-27B-heretic-v3-mxfp8

from llmfan46/Qwen3.5-27B-uncensored-heretic-v1

MXFP8

Vision + text · llmfan46 ↓ 39 · ♥ 0

Params

27B

Weights

≈ 29.5 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-03-28

SmolLM-1.7B-8bit

mlx-community/SmolLM-1.7B-8bit

8-bit

Text generation ↓ 39 · ♥ 0

Params

1.7B

Weights

≈ 1.8 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-07-16

SmolLM-360M-8bit

mlx-community/SmolLM-360M-8bit

8-bit

Text generation ↓ 39 · ♥ 0

Params

362M

Weights

≈ 384 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-07-16

SmolLM3-3B-Base-3bit

from HuggingFaceTB/SmolLM3-3B-Base

3-bit

Text generation · Hugging Face ↓ 39 · ♥ 0

Params

3.1B

Weights

≈ 1.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-07-08

SmolLM3-3B-Base-8bit

from HuggingFaceTB/SmolLM3-3B-Base

8-bit

Text generation · Hugging Face ↓ 39 · ♥ 0

Params

3.1B

Weights

≈ 3.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-07-08

SmolLM3-3B-Base-bf16

from HuggingFaceTB/SmolLM3-3B-Base

bf16

Text generation · Hugging Face ↓ 39 · ♥ 0

Params

3.1B

Weights

≈ 6.2 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-07-08

bark

mlx-community/bark

Uncategorised ↓ 39 · ♥ 0

Params

774M

Weights

≈ 3.1 GB

Mac memory

8 GB+

updated 2026-04-05

bitnet-b1.58-2B-4T-6bit

from microsoft/bitnet-b1.58-2B-4T

6-bit

Text generation · Microsoft · Phi ↓ 39 · ♥ 0

Params

593M

Weights

≈ 495 MB

Mac memory

8 GB+

mit · updated 2025-06-10

dots.mocr-5bit

from dots-studio/dots.mocr

5-bit

Vision + text · dots-studio ↓ 39 · ♥ 0

Params

3.0B

Weights

≈ 3.7 GB

Mac memory

8 GB+

mit · updated 2026-04-03

dots.mocr-mxfp4

from dots-studio/dots.mocr

MXFP4

Vision + text · dots-studio ↓ 39 · ♥ 0

Params

3.0B

Weights

≈ 3.5 GB

Mac memory

8 GB+

mit · updated 2026-04-03

gemma-2-9b-it-SimPO-8bit

from princeton-nlp/gemma-2-9b-it-SimPO

8-bit

Text generation · princeton-nlp ↓ 39 · ♥ 0

Params

9.2B

Weights

≈ 9.8 GB

Mac memory

16 GB+

mit · updated 2025-07-22

granite-4.0-1b-speech-bf16

from ibm-granite/granite-4.0-1b-base

bf16

Uncategorised · IBM · Granite ↓ 39 · ♥ 0

Params

2.3B

Weights

≈ 4.6 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-11

kimi-audio-7b

mlx-community/kimi-audio-7b

Text to speech ↓ 39 · ♥ 0

Params

9.8B

Weights

≈ 19.5 GB

Mac memory

24 GB+

mit · updated 2026-04-05

llm-jp-3.1-1.8b-instruct4

from llm-jp/llm-jp-3.1-1.8b-instruct4

Text generation · llm-jp ↓ 39 · ♥ 0

Params

1.9B

Weights

≈ 3.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-06-16

mathstral-7B-v0.1-8bit

mlx-community/mathstral-7B-v0.1-8bit

8-bit

Uncategorised ↓ 39 · ♥ 0

Params

7.2B

Weights

≈ 7.7 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-07-16

nvidia-Llama-3.1-Nemotron-70B-Reward-HF-AQ41

from nvidia/Llama-3.1-Nemotron-70B-Reward-HF

4-bit

Uncategorised · NVIDIA ↓ 39 · ♥ 0

Params

71B

Weights

≈ 39.7 GB

Mac memory

48 GB+

llama3.1 · updated 2024-10-02

phi-4-abliterated-3bit

from huihui-ai/phi-4-abliterated

3-bit

Text generation · huihui-ai ↓ 39 · ♥ 0

Params

15B

Weights

≈ 6.4 GB

Mac memory

16 GB+

mit · updated 2025-01-09

ui-tars-7b-dpo

mlx-community/ui-tars-7b-dpo

Vision + text ↓ 39 · ♥ 0

Params

8.3B

Weights

≈ 33.2 GB

Mac memory

48 GB+

apache-2.0 · updated 2025-02-11

Qwen3-235B-A22B-3bit-DWQ

from Qwen/Qwen3-235B-A22B

3-bit DWQ

Text generation · Qwen ↓ 38 · ♥ 5

Params

235B

Weights

≈ 103 GB

Mac memory

128 GB+

apache-2.0 · updated 2025-05-15

r1-1776-distill-llama-70b-8bit

from perplexity-ai/r1-1776-distill-llama-70b

8-bit

Uncategorised · perplexity-ai ↓ 38 · ♥ 5

Params

71B

Weights

≈ 75.0 GB

Mac memory

96 GB+

mit · updated 2025-02-21

Nemotron-Research-Reasoning-Qwen-1.5B-8bit

from nvidia/Nemotron-Research-Reasoning-Qwen-1.5B

8-bit

Uncategorised · NVIDIA ↓ 38 · ♥ 2

Params

1.8B

Weights

≈ 1.9 GB

Mac memory

8 GB+

cc-by-nc-4.0 · updated 2025-06-02

Qwen3-4B-Instruct-2507-DDWQ

from Qwen/Qwen3-4B-Instruct-2507

4-bit

Uncategorised · Qwen ↓ 38 · ♥ 2

Params

691M

Weights

≈ 570 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-08-08

SmolLM-360M-Instruct

from HuggingFaceTB/SmolLM-360M

Text generation · Hugging Face ↓ 38 · ♥ 2

Params

362M

Weights

≈ 724 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-08-23

SuperNova-Medius-bf16

from arcee-ai/SuperNova-Medius

bf16

Text generation · arcee-ai ↓ 38 · ♥ 2

Params

15B

Weights

≈ 29.5 GB

Mac memory

48 GB+

apache-2.0 · updated 2024-10-13

aya-23-35B-8bit

mlx-community/aya-23-35B-8bit

8-bit

Text generation ↓ 38 · ♥ 2

Params

35B

Weights

≈ 37.2 GB

Mac memory

48 GB+

cc-by-nc-4.0 · updated 2024-05-23

A.X-4.0-Light-MLX-BF16

from Qwen/Qwen2.5-7B

bf16

Text generation · Qwen ↓ 38 · ♥ 1

Params

7.3B

Weights

≈ 14.5 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-01-20

HY-MT1.5-7B-6bit

from tencent/HY-MT1.5-7B

6-bit

Text generation · tencent ↓ 38 · ♥ 1

Params

7.5B

Weights

≈ 6.1 GB

Mac memory

16 GB+

updated 2026-01-03

Hy3-oQ2e-2.37bpw

from tencent/Hy3

2-bit

Text generation · tencent ↓ 38 · ♥ 1

Params

295B

Weights

≈ 92.3 GB

Mac memory

128 GB+

apache-2.0 · updated 2026-07-15

Jan-v1-edge-4bit

from janhq/Jan-v1-edge

4-bit

Text generation · janhq ↓ 38 · ♥ 1

Params

1.7B

Weights

≈ 968 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-09-04

Josiefied-Qwen3-0.6B-gabliterated-4bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-gabliterated-v1

4-bit

Text generation · Goekdeniz-Guelmez ↓ 38 · ♥ 1

Params

596M

Weights

≈ 335 MB

Mac memory

8 GB+

updated 2026-01-26

LFM2-VL-450M-5bit

mlx-community/LFM2-VL-450M-5bit

5-bit

Vision + text ↓ 38 · ♥ 1

Params

451M

Weights

≈ 423 MB

Mac memory

8 GB+

lfm1.0 · updated 2025-08-16

Llama-3.1-Swallow-8B-Instruct-v0.1-4bit

from tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1

4-bit

Text generation · tokyotech-llm ↓ 38 · ♥ 1

Params

8.0B

Weights

≈ 4.5 GB

Mac memory

8 GB+

llama3.1 · updated 2024-10-08

LongCat-Flash-Thinking-2601-4bit

from meituan-longcat/LongCat-Flash-Thinking-2601

4-bit

Text generation · meituan-longcat ↓ 38 · ♥ 1

Params

561B

Weights

≈ 315 GB

Mac memory

512 GB+

mit · updated 2026-01-17

Nanbeige4-3B-Thinking-2511-gabliterated-bfloat16

from Goekdeniz-Guelmez/Nanbeige4-3B-Thinking-2511-gabliterated

Text generation · Goekdeniz-Guelmez ↓ 38 · ♥ 1

Params

3.9B

Weights

≈ 7.9 GB

Mac memory

16 GB+

updated 2026-01-12

P1-VL-30B-A3B-bf16

from PRIME-RL/P1-VL-30B-A3B

bf16

Vision + text · PRIME-RL ↓ 38 · ♥ 1

Params

31B

Weights

≈ 62.1 GB

Mac memory

96 GB+

apache-2.0 · updated 2026-05-18

Qwen2-Math-1.5B-Instruct-8bit

mlx-community/Qwen2-Math-1.5B-Instruct-8bit

8-bit

Text generation ↓ 38 · ♥ 1

Params

1.5B

Weights

≈ 1.6 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-08-09

Qwen3-4B-Thinking-2507-5bit

from Qwen/Qwen3-4B-Thinking-2507

5-bit

Text generation · Qwen ↓ 38 · ♥ 1

Params

4.0B

Weights

≈ 2.8 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-08-06

Qwen3-4B-Thinking-2507-fp16

from Qwen/Qwen3-4B-Thinking-2507

fp16

Text generation · Qwen ↓ 38 · ♥ 1

Params

4.0B

Weights

≈ 8.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-10-10