deepcogito-cogito-v1-preview-llama-70B-4bit
mlx-community/deepcogito-cogito-v1-preview-llama-70B-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
71B
Weights (est.)
≈ 39.7 GB
Mac memory (est.)
48 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/deepcogito-cogito-v1-preview-llama-70B-4bit --prompt "Hello"
Details
- Base model
- deepcogito/cogito-v1-preview-llama-70B (quantized)
- Vendor
- deepcogito
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3.1
- Downloads
- 27 in the last 30 days · 408 all time · 1 likes
- Published
- 2025-04-09 · updated 2025-04-09 (1y ago)
- Tags
- llama
Other MLX builds of deepcogito/cogito-v1-preview-llama-70B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| deepcogito-cogito-v1-preview-llama-70B-4bit (this one) | 4-bit | ≈ 39.7 GB | 48 GB+ | 27 |
| deepcogito-cogito-v1-preview-llama-70B-6bit | 6-bit | ≈ 57.3 GB | 96 GB+ | 27 |
| deepcogito-cogito-v1-preview-llama-70B-8bit | 8-bit | ≈ 75.0 GB | 96 GB+ | 27 |
| deepcogito-cogito-v1-preview-llama-70B-fp16 | fp16 | ≈ 141 GB | 192 GB+ | 30 |
| deepcogito-cogito-v1-preview-llama-70B-bf16 | bf16 | ≈ 141 GB | 192 GB+ | 20 |