deepcogito · First MLX build 8 Apr 2025
cogito-v1-preview-qwen-14B
MLX
Text apache-2.0
A 15B parameter text generation model from deepcogito, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 15B From Hugging Face
- Quantisation
- 8-bit deepcogito-cogito-v1-preview-qwen-14B-8bit
- Memory needed
- 20 GB Estimate, unified memory
- Download
- 15.7 GB Weights, estimated
- Downloads
- 35 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 20 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/deepcogito-cogito-v1-preview-qwen-14B-8bit --prompt "Hello"MLX builds
5 on mlx-community| deepcogito-cogito-v1-preview-qwen-14B-4bit | 4-bit | 8.3 GB | 12 GB | 30 |
|---|---|---|---|---|
| deepcogito-cogito-v1-preview-qwen-14B-6bit | 6-bit | 12.0 GB | 16 GB | 31 |
| deepcogito-cogito-v1-preview-qwen-14B-8bit | 8-bit | 15.7 GB | 20 GB | 35 |
| deepcogito-cogito-v1-preview-qwen-14B-fp16 | fp16 | 29.5 GB | 36 GB | 28 |
| deepcogito-cogito-v1-preview-qwen-14B-bf16 | bf16 | 29.5 GB | 36 GB | 18 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.