Configuration Parsing Warning: In config.json: "quantization_config.bits" must be an integer
EXL3 3.5bpw Quant of https://huggingface.co/DreadPoor/Irix-12B-Model_Stock
Will fit on a 8GB card with 16k context with Q8 K/V cache.
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for RossAscends/12B-Irix-Model-Stock-EXL3-3.5bpw
Base model
DreadPoor/Irix-12B-Model_Stock