Llama-3.3-Swallow-70B-Instruct-v0.4-8bit
mlx-community/Llama-3.3-Swallow-70B-Instruct-v0.4-8bit
Text generation · transformers
8-bit Open on Hugging Face
Parameters
71B
Weights (est.)
≈ 75.0 GB
Mac memory (est.)
96 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/Llama-3.3-Swallow-70B-Instruct-v0.4-8bit --prompt "Hello"
Details
- Base model
- tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4 (quantized)
- Vendor
- tokyotech-llm
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- llama3.3
- Downloads
- 191 in the last 30 days · 1.9K all time · 1 likes
- Published
- 2025-03-10 · updated 2025-03-10 (1y ago)
- Languages
- en, ja
- Tags
- llama
Other MLX builds of tokyotech-llm/Llama-3.3-Swallow-70B-Instruct-v0.4
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Llama-3.3-Swallow-70B-Instruct-v0.4-4bit | 4-bit | ≈ 39.7 GB | 48 GB+ | 106 |
| Llama-3.3-Swallow-70B-Instruct-v0.4-8bit (this one) | 8-bit | ≈ 75.0 GB | 96 GB+ | 191 |