# 8-bit quantization
ERNIE 4.5 21B A3B PT 8bit
Apache-2.0
ERNIE-4.5-21B-A3B-PT-8bit is an 8-bit quantized version of Baidu's ERNIE-4.5-21B-A3B-PT model, converted to MLX format and suitable for Apple Silicon devices.
Large Language Model Supports Multiple Languages
E
mlx-community
123
1
Jan Nano 8bit
Apache-2.0
Jan-nano-8bit is an 8-bit quantized version converted from the Menlo/Jan-nano model, optimized for the MLX framework and suitable for text generation tasks.
Large Language Model
J
mlx-community
188
1
Josiefied DeepSeek R1 0528 Qwen3 8B Abliterated V1 8bit
This is an 8-bit quantized version in MLX format converted from the DeepSeek-R1-0528-Qwen3-8B model, suitable for text generation tasks.
Large Language Model
J
mlx-community
847
1
Deepseek R1 0528 Qwen3 8B MLX 8bit
MIT
An 8-bit quantized version based on the DeepSeek-R1-0528-Qwen3-8B model, optimized for Apple Silicon chips and suitable for text generation tasks.
Large Language Model
D
lmstudio-community
151.87k
2
Devstral Small 2505 8bit
Apache-2.0
Devstral-Small-2505-8bit is an 8-bit quantized model converted from mistralai/Devstral-Small-2505, suitable for the MLX framework and supporting text generation tasks in multiple languages.
Large Language Model Supports Multiple Languages
D
mlx-community
789
1
Fastvlm 1.5B Stage3 MNN
Apache-2.0
FastVLM-1.5B-Stage3-MNN is a text generation model based on the Transformer architecture. It is an 8-bit quantized version of FastVLM-1.5B-Stage3, suitable for text generation scenarios such as chatting.
Large Language Model English
F
taobao-mnn
1,157
1
Spark TTS 0.5B 8bit
This is a text-to-speech model based on the MLX format, supporting both English and Chinese, converted from prince-canuma/Spark-TTS-0.5B.
Speech Synthesis Supports Multiple Languages
S
mlx-community
56
1
Csm 1b 8bit
Apache-2.0
This is a text-to-speech model converted from sesame/csm-1b to MLX format, supporting the English language.
Speech Synthesis Supports Multiple Languages
C
mlx-community
36
0
Qwen3 235B A22B 8bit
Apache-2.0
This model is an 8-bit quantized version converted from Qwen/Qwen3-235B-A22B, suitable for text generation tasks.
Large Language Model
Q
mlx-community
477
2
Orpheus 3b Korean FT Q8 0.gguf
Apache-2.0
Orpheus is a high-performance Korean text-to-speech model, fine-tuned for natural emotional speech synthesis, offering an 8-bit quantized version for optimized efficiency.
Speech Synthesis Supports Multiple Languages
O
lex-au
29
0
Orpheus 3b German FT Q8 0.gguf
Apache-2.0
Orpheus is a high-performance German text-to-speech model, fine-tuned to achieve natural and emotionally rich speech synthesis. This model is an 8-bit quantized version of the 3-billion-parameter model, optimized for operational efficiency.
Speech Synthesis Supports Multiple Languages
O
lex-au
130
3
Gemma 3 27b It Qat 8bit
Other
Gemma 3 27B IT QAT 8bit is an MLX-format model converted from Google's Gemma 3 27B model, supporting image-to-text tasks.
Image-to-Text
Transformers Other

G
mlx-community
422
2
Orpheus 3b 0.1 Pretrained 8bit
Apache-2.0
This is an 8-bit quantized version of the Orpheus-3B pre-trained language model based on the MLX framework, originally developed by CanopyLabs.
Large Language Model English
O
mlx-community
15
1
Omnigen V1 Bnb 8bit
MIT
The 8-bit quantized version of OmniGen-v1, suitable for text-to-image and image-to-image tasks, supporting multimodal input.
Text-to-Image
O
gryan
76
0
Gpt J 6B 8bit
Apache-2.0
This is the 8-bit quantized version of EleutherAI's GPT-J 6B parameter model, optimized for running and fine-tuning on limited GPU resources (e.g., Colab or 1080Ti).
Large Language Model
Transformers English

G
hivemind
176
131
Featured Recommended AI Models