Devstral-Small-2507-6bit
from mlx-community/Devstral-Samll-2507-bf16
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-07-11
Apple silicon
Apple MLX models
5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 40m ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
2,922 builds · page 22 of 49 · clear filters
HY-MT1.5-1.8B-6bit
from tencent/HY-MT1.5-1.8B
Params
1.8B
Weights
≈ 1.5 GB
Mac memory
8 GB+
updated 2026-01-03
Llama-3-Groq-70B-Tool-Use-4bit
mlx-community/Llama-3-Groq-70B-Tool-Use-4bit
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+
llama3 · updated 2024-07-17
Qwen3-18B-A3B-Stranger-Thoughts-Q_6
from DavidAU/Qwen3-18B-A3B-Stranger-Thoughts
Params
17B
Weights
≈ 14.1 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-06-28
TinyMistral-248M-8bits
mlx-community/TinyMistral-248M-8bits
Params
248M
Weights
≈ 264 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-28
codegemma-1.1-7b-it-4bit
mlx-community/codegemma-1.1-7b-it-4bit
Params
8.5B
Weights
≈ 4.8 GB
Mac memory
8 GB+
gemma · updated 2024-05-03
glm-4-9b-chat-1m-6bit
from zai-org/glm-4-9b-chat-1m-hf
Params
9.5B
Weights
≈ 7.7 GB
Mac memory
16 GB+
glm-4 · updated 2025-09-14
AI21-Jamba-Reasoning-3B-bf16
from ai21labs/AI21-Jamba-Reasoning-3B
Params
3.0B
Weights
≈ 6.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-10-14
Dolphin-Mistral-24B-Venice-Edition-5bit
from dphn/Dolphin-Mistral-24B-Venice-Edition
Params
24B
Weights
≈ 16.2 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-07-06
Qwen2.5-1.5B-8bit
mlx-community/Qwen2.5-1.5B-8bit
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-09-18
bitnet-b1.58-2B-4T-8bit
from microsoft/bitnet-b1.58-2B-4T
Params
614M
Weights
≈ 662 MB
Mac memory
8 GB+
mit · updated 2025-06-10
gemma-3-4b-it-wikisql-finetuned-4bit
from mlx-community/gemma-3-4b-it-qat-4bit
Params
4.6B
Weights
≈ 2.6 GB
Mac memory
8 GB+
qwen · updated 2025-08-30
llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-4bit
mlx-community/llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-4bit
Params
14B
Weights
≈ 7.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2024-04-30
llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-8bit
mlx-community/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-8bit
Params
14B
Weights
≈ 14.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-04-30
Jan-nano-8bit
from Menlo/Jan-nano
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-06-16
QwQ-32B-Preview-3bit
from Qwen/QwQ-32B-Preview
Params
33B
Weights
≈ 14.3 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-11-28
QwQ-32B-6bit
from Qwen/QwQ-32B
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+
apache-2.0 · updated 2025-03-05
Llama-4-Maverick-17B-16E-Instruct-6bit
from meta-llama/Llama-4-Maverick-17B-128E-Instruct
Params
401B
Weights
≈ 326 GB
Mac memory
512 GB+
llama4 · updated 2025-04-06
meta-llama-Llama-4-Scout-17B-16E-bf16
from meta-llama/Llama-4-Scout-17B-16E
Params
108B
Weights
≈ 216 GB
Mac memory
256 GB+
llama4 · updated 2025-04-06
LFM2.5-2.6B-bf16
from LiquidAI/LFM2.5-2.6B
Params
2.7B
Weights
≈ 5.4 GB
Mac memory
16 GB+
lfm1.0 · updated 2026-08-13
DeepSeek-R1-Distill-Qwen-32B-float16
from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+
mit · updated 2025-06-20
GLM-Z1-9B-0414-abliterated-6bit
from huihui-ai/GLM-Z1-9B-0414-abliterated
Params
9.4B
Weights
≈ 7.6 GB
Mac memory
16 GB+
mit · updated 2025-04-26
Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-4bit
from Goekdeniz-Guelmez/Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-11-17
Josiefied-Qwen3-4B-Instruct-2507-abliterated-v2-8bit
from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-abliterated-v2
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
updated 2026-03-14
Qwen2.5-7B-Instruct-kowiki-qa-4bit
mlx-community/Qwen2.5-7B-Instruct-kowiki-qa-4bit
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-12-20
Qwen3-0.6B-Base-DQ5
from mlx-community/Qwen3-0.6B-Base-bf16
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-12-25
gemma-2-27b-it-bf16-8bit
from google/gemma-2-27b-it
Params
27B
Weights
≈ 28.9 GB
Mac memory
48 GB+
gemma · updated 2024-11-06
llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-8bit
mlx-community/llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-8bit
Params
14B
Weights
≈ 14.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-04-30
LFM2-8B-A1B-8bit-MLX
from LiquidAI/LFM2-8B-A1B
Params
8.3B
Weights
≈ 8.9 GB
Mac memory
16 GB+
lfm1.0 · updated 2025-10-08
MiniMax-M2.5-6bit
from MiniMaxAI/MiniMax-M2.5
Params
229B
Weights
≈ 186 GB
Mac memory
256 GB+
modified-mit · updated 2026-02-13
Josiefied-Qwen3-4B-abliterated-v1-6bit
from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
updated 2025-05-01
Devstral-Samll-2507-bf16
from mistralai/Devstral-Small-2507
Params
24B
Weights
≈ 47.1 GB
Mac memory
64 GB+
apache-2.0 · updated 2025-07-10
Qwen2-1.5B-Instruct-4bit
mlx-community/Qwen2-1.5B-Instruct-4bit
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-06
Seed-Coder-8B-Reasoning-6bit
from ByteDance-Seed/Seed-Coder-8B-Reasoning
Params
8.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+
mit · updated 2025-05-20
GLM-4-9B-0414-bf16
from zai-org/GLM-4-9B-0414
Params
9.4B
Weights
≈ 18.8 GB
Mac memory
24 GB+
mit · updated 2025-04-17
Hermes-4-14B-5bit
from NousResearch/Hermes-4-14B
Params
15B
Weights
≈ 10.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-09-03
Mellum2-12B-A2.5B-Instruct-6bit
from JetBrains/Mellum2-12B-A2.5B-Instruct
Params
12B
Weights
≈ 9.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-08-11
Qwen2.5-Coder-0.5B-4bit-gs32
from Qwen/Qwen2.5-Coder-0.5B
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-01-13
Qwen3-0.6B-Base-8bit
from Qwen/Qwen3-0.6B-Base
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-12-25
RAI-3.0-R1-VECTOR-MLX-4bit
from Local-Novel-LLM-project/RAI-3.0-R1-VECTOR
Params
671B
Weights
≈ 378 GB
Mac memory
512 GB+
apache-2.0 · updated 2026-05-01
SmolLM2-360M-Instruct-bf16-mlx
from HuggingFaceTB/SmolLM2-360M-Instruct
Params
362M
Weights
≈ 724 MB
Mac memory
8 GB+
apache-2.0 · updated 2025-02-25
medgemma-27b-text-it-6bit
from google/medgemma-27b-text-it
Params
28B
Weights
≈ 23.1 GB
Mac memory
32 GB+
health-ai-developer-foundations · updated 2025-06-09
GLM-4.5-Air-2bit
from zai-org/GLM-4.5-Air
Params
107B
Weights
≈ 33.4 GB
Mac memory
48 GB+
mit · updated 2025-07-28
Youtu-LLM-2B-4bit
from tencent/Youtu-LLM-2B
Params
2.2B
Weights
≈ 1.3 GB
Mac memory
8 GB+
tencent-youtu · updated 2026-01-01
LFM2-8B-A1B-6bit-MLX
from LiquidAI/LFM2-8B-A1B
Params
8.3B
Weights
≈ 6.8 GB
Mac memory
16 GB+
lfm1.0 · updated 2025-10-08
Qwen2.5-14B-8bit
mlx-community/Qwen2.5-14B-8bit
Params
15B
Weights
≈ 15.7 GB
Mac memory
24 GB+
apache-2.0 · updated 2024-09-18
SmolLM3-3B-bf16
from HuggingFaceTB/SmolLM3-3B
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-07-08
Falcon-H1-Tiny-Tool-Calling-90M-4bit
from tiiuae/Falcon-H1-Tiny-Tool-Calling-90M
Params
91M
Weights
≈ 51 MB
Mac memory
8 GB+
falcon-llm-license · updated 2026-01-28
Llama-3-Groq-70B-Tool-Use-8bit
mlx-community/Llama-3-Groq-70B-Tool-Use-8bit
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+
llama3 · updated 2024-07-17
Ring-1T-preview-3bit
from inclusionAI/Ring-1T-preview
Params
1000B
Weights
≈ 437 GB
Mac memory
512 GB+
mit · updated 2025-09-29
meta-llama-Llama-4-Scout-17B-16E-6bit
from meta-llama/Llama-4-Scout-17B-16E
Params
108B
Weights
≈ 87.6 GB
Mac memory
128 GB+
llama4 · updated 2025-04-06
Josiefied-Hermes-3-Llama-3.2-3B-v1-8bit
from Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+
updated 2025-10-28
Llama-3.1-Swallow-70B-Instruct-v0.1
from tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.1
Params
71B
Weights
≈ 141 GB
Mac memory
192 GB+
llama3.1 · updated 2024-10-08
Meta-Llama-3.1-8B-Instruct-4bit-fakenews
from meta-llama/Llama-3.1-8B-Instruct
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
llama3.1 · updated 2024-11-07
MiniCPM4.1-8B-4bit
from openbmb/MiniCPM4.1-8B
Params
8.2B
Weights
≈ 4.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-09-08
Qwen2.5-72B-Instruct-bf16
from Qwen/Qwen2.5-72B
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+
qwen · updated 2024-09-19
Qwen3-235B-A22B-Instruct-2507-3bit
from Qwen/Qwen3-235B-A22B-Instruct-2507
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+
apache-2.0 · updated 2025-07-22
Qwen3-4B-Thinking-2507-heretic-8bit
from Daizee/Qwen3-4B-Thinking-2507-heretic
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-02-16
gemma-3-270m-4bit
from google/gemma-3-270m
Params
436M
Weights
≈ 245 MB
Mac memory
8 GB+
gemma · updated 2025-08-09
gemma-3-text-12b-pt-4bit
from mlx-community/gemma-3-12b-pt-bf16
Params
13B
Weights
≈ 7.2 GB
Mac memory
16 GB+
gemma · updated 2025-03-18