Just some GGUF v2 quantizations of the model TinyLlama/tinyLlama-intermediate-checkpoints Step 480K pretrained on 1T of tokens.
q2_k, q4_0, q4_1, q5_0, q5_1, q8_0 and f16.
- Downloads last month
- 26
Hardware compatibility
Log In
to view the estimation
2-bit
4-bit
5-bit
8-bit
16-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support