Llama-3.1-Swallow-70B-Instruct-v0.3-4bit
mlx-community/Llama-3.1-Swallow-70B-Instruct-v0.3-4bit
Text generation · transformers
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/Llama-3.1-Swallow-70B-Instruct-v0.3-4bit --prompt "Hello"
Details
- Base model
- tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3 (quantized)
- Vendor
- tokyotech-llm
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- llama3.1
- Downloads
- 117 in the last 30 days · 654 all time · 0 likes
- Published
- 2025-03-10 · updated 2025-03-10 (1y ago)
- Languages
- en, ja
- Tags
- llama
Other MLX builds of tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Llama-3.1-Swallow-70B-Instruct-v0.3-4bit (this one) | 4-bit | ≈ 39.7 GB | 48 GB+ | 117 |
| Llama-3.1-Swallow-70B-Instruct-v0.3-8bit | 8-bit | ≈ 75.0 GB | 96 GB+ | 49 |