XortronCriminalComputingConfig-mlx-8Bit
mlx-community/XortronCriminalComputingConfig-mlx-8Bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
24B
Weights (est.)
≈ 25.0 GB
Mac memory (est.)
32 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/XortronCriminalComputingConfig-mlx-8Bit --prompt "Hello"
Details
- Base model
- darkc0de/XortronCriminalComputingConfig (quantized)
- Vendor
- darkc0de
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- wtfpl
- Downloads
- 43 in the last 30 days · 941 all time · 4 likes
- Published
- 2025-06-19 · updated 2025-06-19 (1y ago)
- Languages
- en
- Tags
- mistral, mergekit, merge, uncensored, harmful, mlx-my-repo
Other MLX builds of darkc0de/XortronCriminalComputingConfig
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| XortronCriminalComputingConfig-4bit | 4-bit | ≈ 13.3 GB | 24 GB+ | 28 |
| XortronCriminalComputingConfig-mxfp4 | MXFP4 | ≈ 13.3 GB | 24 GB+ | 21 |
| XortronCriminalComputingConfig-6bit | 6-bit | ≈ 19.2 GB | 24 GB+ | 24 |
| XortronCriminalComputingConfig-mlx-8Bit (this one) | 8-bit | ≈ 25.0 GB | 32 GB+ | 43 |
| XortronCriminalComputingConfig-8bit | 8-bit | ≈ 25.0 GB | 32 GB+ | 18 |
| XortronCriminalComputingConfig-bfloat16 | — | ≈ 47.1 GB | 64 GB+ | 18 |