karakuri-lm-8x7b-instruct-v0.1-8bit
mlx-community/karakuri-lm-8x7b-instruct-v0.1-8bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
47B
Weights (est.)
≈ 49.6 GB
Mac memory (est.)
64 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/karakuri-lm-8x7b-instruct-v0.1-8bit --prompt "Hello"
Details
- Base model
- karakuri-ai/karakuri-lm-8x7b-instruct-v0.1 (quantized)
- Vendor
- karakuri-ai
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- apache-2.0
- Downloads
- 26 in the last 30 days · 347 all time · 0 likes
- Published
- 2024-10-11 · updated 2024-10-11 (2y ago)
- Languages
- en, ja
- Tags
- mixtral, steerlm
Other MLX builds of karakuri-ai/karakuri-lm-8x7b-instruct-v0.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| karakuri-lm-8x7b-instruct-v0.1-4bit | 4-bit | ≈ 26.3 GB | 32 GB+ | 30 |
| karakuri-lm-8x7b-instruct-v0.1-8bit (this one) | 8-bit | ≈ 49.6 GB | 64 GB+ | 26 |
| karakuri-lm-8x7b-instruct-v0.1 | — | ≈ 93.4 GB | 128 GB+ | 49 |