by meta-llama
Llama 3.2 1B Instruct
meta-llama/Llama-3.2-1B-Instruct
All figures are estimates. Real memory use and speed depend on your drivers, settings and other programs running.
- Parameters
- 1.2B
- Licence
- llama3.2
- Published
- Sep 18, 2024
The licence is the model maker’s. Check its terms before you use the model.
Hugging Face asks you to accept the maker’s terms before you download this model. No kit is sold for it.
Original on Hugging Face ↗Memory needed by quantization
At 8,192 tokens of context, including 0.8 GB for the runtime.
| Quantization | Model file | Total |
|---|---|---|
| Q4_K_M | 0.7 GB | 1.6 GB(rough) |
| Q5_K_M | 0.9 GB | 1.8 GB(rough) |
| Q6_K | 1.0 GB | 1.9 GB(rough) |
| Q8_0 | 1.3 GB | 2.2 GB(rough) |
| F16 | 2.5 GB | 3.5 GB(rough) |
Hardware that runs it on the graphics card
At Q4_K_M and 8,192 tokens of context.
- NVIDIA GeForce RTX 3060 (12 GB)
- NVIDIA GeForce RTX 3070
- NVIDIA GeForce RTX 3080 (10 GB)
- NVIDIA GeForce RTX 3090
- NVIDIA GeForce RTX 4070
- NVIDIA GeForce RTX 4070 Ti SUPER
- NVIDIA GeForce RTX 4080 SUPER
- NVIDIA GeForce RTX 4090
- NVIDIA GeForce RTX 5060 Ti (16 GB)
- NVIDIA GeForce RTX 5070
- NVIDIA GeForce RTX 5070 Ti
- NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 5090
- AMD Radeon RX 7600
- AMD Radeon RX 7700 XT
- AMD Radeon RX 7800 XT
- AMD Radeon RX 7900 XT
- AMD Radeon RX 7900 XTX
- AMD Radeon RX 9070 XT
- Apple M1 Pro
- Apple M1 Max
- Apple M2
- Apple M2 Pro
- Apple M2 Max
- Apple M3
- Apple M3 Pro
- Apple M3 Max (30-core GPU)
- Apple M3 Max (40-core GPU)
- Apple M4
- Apple M4 Pro
- Apple M4 Max (32-core GPU)
- Apple M4 Max (40-core GPU)
- Apple M5
- AMD Ryzen AI Max+ 395
The same model through an API
Cheapest seller: Inference, $0.09 a month at the default use (200 requests a day).
See the prices on the Model Price MapModel details come from Hugging Face’s public listings (names, sizes, licences). Every model page links to the original.