Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization Paper • 2509.23202 • Published Sep 27 • 27
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm Paper • 2507.18553 • Published Jul 24 • 40
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb 12B • Updated Oct 21, 2024
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb 12B • Updated Oct 21, 2024
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipTrue_fineweb 12B • Updated Oct 21, 2024
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb 2B • Updated Oct 26, 2024
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb 2B • Updated Oct 26, 2024
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipTrue_fineweb 2B • Updated Oct 26, 2024
daslab-testing/Qwen2.5-7B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipFalse_fineweb 2B • Updated Oct 26, 2024
daslab-testing/Qwen2.5-72B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipFalse_fineweb Updated Oct 19, 2024
daslab-testing/Llama-3.1-Nemotron-70B-Instruct-HF-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb 11B • Updated Oct 18, 2024
daslab-testing/Llama-3.1-Nemotron-70B-Instruct-HF-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb Updated Oct 18, 2024
daslab-testing/Llama-3.1-Nemotron-70B-Instruct-HF-gptq4-128-True-seed1_mse1_staticFalse_clipFalse_fineweb 11B • Updated Oct 18, 2024
daslab-testing/Llama-3.1-70B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipTrue_fineweb 11B • Updated Oct 17, 2024
daslab-testing/Llama-3.1-70B-Instruct-gptq4-128-True-seed1_mse1_staticTrue_clipFalse_fineweb 11B • Updated Oct 17, 2024
daslab-testing/Llama-3.1-70B-Instruct-gptq4-128-True-seed1_mse1_staticFalse_clipTrue_fineweb 11B • Updated Oct 17, 2024