Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 53m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

68 builds · page 1 of 2 · clear filters

Qwen3-4B-Instruct-2507-4bit

from Qwen/Qwen3-4B-Instruct-2507
4-bit
Text generation · Qwen ↓ 95K · ♥ 18
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-02

Qwen3-4B-4bit

from Qwen/Qwen3-4B
4-bit
Text generation · Qwen ↓ 30K · ♥ 17
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Josiefied-Qwen3-4B-abliterated-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
4-bit
Text generation · Goekdeniz-Guelmez ↓ 4.1K · ♥ 8
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

updated 2025-05-01

Qwen3-4B-8bit

from Qwen/Qwen3-4B
8-bit
Text generation · Qwen ↓ 1.7K · ♥ 1
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-4B-Instruct-2507-4bit-DWQ-2510

from Qwen/Qwen3-4B-Instruct-2507
4-bit DWQ
Text generation · Qwen ↓ 1.1K · ♥ 2
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-13

Qwen3-4B-Thinking-2507-4bit

from Qwen/Qwen3-4B-Thinking-2507
4-bit
Text generation · Qwen ↓ 891 · ♥ 4
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-06

Qwen3-Reranker-4B-mxfp8

from Qwen/Qwen3-4B-Base
MXFP8
Reranking · Qwen ↓ 887 · ♥ 2
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-11

Qwen3-Embedding-4B-mxfp8

from Qwen/Qwen3-4B-Base
MXFP8
Embeddings · Qwen ↓ 854 · ♥ 2
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-11

Qwen3-4B-Instruct-2507-8bit

from Qwen/Qwen3-4B-Instruct-2507
8-bit
Text generation · Qwen ↓ 821 · ♥ 5
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-06

Qwen3-4B-Instruct-2507-bf16

from Qwen/Qwen3-4B-Instruct-2507
bf16
Text generation · Qwen ↓ 292 · ♥ 2
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-01-07

Qwen3-4B-bf16

from Qwen/Qwen3-4B
bf16
Text generation · Qwen ↓ 246 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-04-28

Qwen3-4B-Instruct-2507-gabliterated-4bit

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
4-bit
Text generation · Goekdeniz-Guelmez ↓ 225 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

updated 2026-01-06

Qwen3-4B-Instruct-2507-6bit

from Qwen/Qwen3-4B-Instruct-2507
6-bit
Text generation · Qwen ↓ 221 · ♥ 1
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-06

Qwen3-4B-Instruct-2507-nvfp4

from Qwen/Qwen3-4B-Instruct-2507
4-bit
Text generation · Qwen ↓ 185 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-08

Qwen3-4B-4bit-DWQ

from Qwen/Qwen3-4B
4-bit DWQ
Text generation · Qwen ↓ 177 · ♥ 4
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-05-31

Qwen3-4B-3bit

from Qwen/Qwen3-4B
3-bit
Text generation · Qwen ↓ 172 · ♥ 0
Params
4.0B
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-4B-Thinking-2507-heretic-4bit

from Daizee/Qwen3-4B-Thinking-2507-heretic
4-bit
Text generation · Daizee ↓ 170 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-16

Qwen3-4B-Instruct-2507-mxfp8

from Qwen/Qwen3-4B-Instruct-2507
MXFP8
Text generation · Qwen ↓ 168 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-08

Qwen3-4B-Instruct-2507-5bit

from Qwen/Qwen3-4B-Instruct-2507
5-bit
Text generation · Qwen ↓ 164 · ♥ 1
Params
4.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-09

Qwen3-4B-Sky-High-Hermes-8bit

from ZeroXClem/Qwen3-4B-Sky-High-Hermes
8-bit
Text generation · ZeroXClem ↓ 160 · ♥ 2
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-19

Qwen3-4B-4bit-DWQ-053125

from Qwen/Qwen3-4B
4-bit DWQ
Text generation · Qwen ↓ 151 · ♥ 2
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-01

Qwen3-4B-Thinking-2507-8bit

from Qwen/Qwen3-4B-Thinking-2507
8-bit
Text generation · Qwen ↓ 138 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-06

Qwen3-4B-Instruct-2507-4bit-g32

from Qwen/Qwen3-4B-Instruct-2507
4-bit
Text generation · Qwen ↓ 90 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-11

Qwen3-4B-6bit

from Qwen/Qwen3-4B
6-bit
Text generation · Qwen ↓ 82 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-4B-Instruct-2507-mxfp4

from Qwen/Qwen3-4B-Instruct-2507
MXFP4
Text generation · Qwen ↓ 82 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-08

Qwen3-4B-ARC-MLX-4bit

from sorokin/qwen3_4b_grids15_sft139
4-bit
Text generation · sorokin ↓ 76 · ♥ 2
Params
3.6B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-04

Qwen3-4B-Sky-High-Hermes-gabliterated-4bit

from Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
4-bit
Text generation · Goekdeniz-Guelmez ↓ 76 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

updated 2026-01-23

Qwen3-4B-Instruct-2507-5bit-g32

from Qwen/Qwen3-4B-Instruct-2507
5-bit
Text generation · Qwen ↓ 71 · ♥ 0
Params
4.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-11

Josiefied-Qwen3-4B-abliterated-v1-6bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
6-bit
Text generation · Goekdeniz-Guelmez ↓ 63 · ♥ 2
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

updated 2025-05-01

Qwen3-4B-Thinking-2507-heretic-8bit

from Daizee/Qwen3-4B-Thinking-2507-heretic
8-bit
Text generation · Daizee ↓ 62 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-16

Qwen3-4B-Instruct-2507-gabliterated-mxfp4

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
MXFP4
Text generation · Goekdeniz-Guelmez ↓ 59 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

updated 2026-01-06

Josiefied-Qwen3-4B-abliterated-v1-bf16

from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
bf16
Text generation · Goekdeniz-Guelmez ↓ 58 · ♥ 1
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2025-05-01

Qwen3-4B-Instruct-2507-gabliterated-8bit

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
8-bit
Text generation · Goekdeniz-Guelmez ↓ 57 · ♥ 1
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2026-01-06

Qwen3-4B-Instruct-2507-gabliterated-6bit

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
6-bit
Text generation · Goekdeniz-Guelmez ↓ 54 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

updated 2026-01-06

Qwen3-4B-Sky-High-Hermes-gabliterated-8bit

from Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
8-bit
Text generation · Goekdeniz-Guelmez ↓ 54 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2026-01-23

Qwen3-4B-Instruct-2507-5.0bpw-dynamic

from Qwen/Qwen3-4B-Instruct-2507
4-bit
Text generation · Qwen ↓ 47 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-11

Qwen3-4B-Instruct-2507-gabliterated-bf16

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated
bf16
Text generation · Goekdeniz-Guelmez ↓ 46 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2026-01-06

Qwen3-4B-Sky-High-Hermes-gabliterated-bfloat16

from Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
Text generation · Goekdeniz-Guelmez ↓ 44 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2026-01-23

Qwen3-4B-Sky-High-Hermes-6bit

from ZeroXClem/Qwen3-4B-Sky-High-Hermes
6-bit
Text generation · ZeroXClem ↓ 42 · ♥ 1
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-19

Josiefied-Qwen3-4B-abliterated-v1-8bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
8-bit
Text generation · Goekdeniz-Guelmez ↓ 40 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2025-05-01

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

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

Qwen3-4B-Thinking-2507-gabliterated-8bit

from Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
8-bit
Text generation · Goekdeniz-Guelmez ↓ 37 · ♥ 1
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

updated 2026-01-17

Qwen3-4B-Thinking-2507-gabliterated-4bit

from Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
4-bit
Text generation · Goekdeniz-Guelmez ↓ 36 · ♥ 2
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

updated 2026-01-17

Qwen3-4B-4bit-DWQ-calibration-1332

from Qwen/Qwen3-4B
4-bit DWQ
Text generation · Qwen ↓ 33 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-05-11

Qwen3-4B-Sky-High-Hermes-4bit

from ZeroXClem/Qwen3-4B-Sky-High-Hermes
4-bit
Text generation · ZeroXClem ↓ 33 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-19

Qwen3-4B-Sky-High-Hermes-gabliterated-6bit

from Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated
6-bit
Text generation · Goekdeniz-Guelmez ↓ 33 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

updated 2026-01-23