Uploaded model

  • Developed by: fireworks1231
  • License: apache-2.0
  • Finetuned from model : fireworks1231/lightning-2509

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
90
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for fireworks1231/lightning-2509-gguf

Quantized
(2)
this model