DeepSeek-R1-Distill-Llama-70B EXL2 7.0bpw h6

EXL2 quantization of deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Quantization Details

  • Format: EXL2
  • Bits per weight: 7.0bpw
  • Head bits: 6
  • Quantized with: ExLlamaV2 0.3.1
  • Calibration: Default ExLlamaV2 calibration dataset

Hardware Requirements

  • Minimum VRAM: ~40GB (e.g. 2x RTX 3090)
  • Recommended: 48GB+ for comfortable context

Usage

Load with TabbyAPI or text-generation-webui with ExLlamaV2 loader.

Original Model

See deepseek-ai/DeepSeek-R1-Distill-Llama-70B for full details, license, and usage recommendations.

Downloads last month
18
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support