Inference Optimization

community

AI & ML interests

None defined yet.

Recent Activity

nm-research updated a model about 1 hour ago

inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step42008

nm-research published a model about 1 hour ago

inference-optimization/Qwen3-8B-speculator.dflash.swa.non-qwen3-step42008

ChibuUkachi updated a dataset about 6 hours ago

inference-optimization/every-eval-ever-demo

View all activity

inference-optimization 's models 387

inference-optimization/qwen3_8b_7.0_bits_mode_heuristic_stiched

7B • Updated May 8 • 4

inference-optimization/qwen3_8b_6.5_bits_mode_noise_stiched

7B • Updated May 8 • 4

inference-optimization/qwen3_8b_6.5_bits_mode_hybrid_stiched

7B • Updated May 8 • 4

inference-optimization/qwen3_8b_6.5_bits_mode_heuristic_stiched

7B • Updated May 8 • 5

inference-optimization/qwen3_8b_6.0_bits_mode_noise_stiched

6B • Updated May 8 • 4

inference-optimization/qwen3_8b_6.0_bits_mode_hybrid_stiched

6B • Updated May 8 • 4

inference-optimization/qwen3_8b_6.0_bits_mode_heuristic_stiched

6B • Updated May 8 • 3

inference-optimization/qwen3_8b_5.5_bits_mode_noise_stiched

6B • Updated May 8 • 4

inference-optimization/qwen3_8b_5.5_bits_mode_hybrid_stiched

6B • Updated May 8 • 3

inference-optimization/qwen3_8b_5.5_bits_mode_heuristic_stiched

6B • Updated May 8 • 5

inference-optimization/qwen3_8b_5.0_bits_mode_noise_stiched

6B • Updated May 8 • 3

inference-optimization/qwen3_8b_5.0_bits_mode_hybrid_stiched

6B • Updated May 8 • 5

inference-optimization/qwen3_8b_5.0_bits_mode_heuristic_stiched

6B • Updated May 8 • 3

inference-optimization/llama3_8b_7.0_bits_mode_noise_stiched

7B • Updated May 8 • 3

inference-optimization/llama3_8b_7.0_bits_mode_hybrid_stiched

7B • Updated May 8 • 3

inference-optimization/llama3_8b_7.0_bits_mode_heuristic_stiched

7B • Updated May 8 • 3

inference-optimization/llama3_8b_6.5_bits_mode_noise_stiched

7B • Updated May 8 • 3

inference-optimization/llama3_8b_6.5_bits_mode_hybrid_stiched

7B • Updated May 8 • 3

inference-optimization/llama3_8b_6.5_bits_mode_heuristic_stiched

7B • Updated May 8 • 3

inference-optimization/llama3_8b_6.0_bits_mode_noise_stiched

6B • Updated May 8 • 3

inference-optimization/llama3_8b_6.0_bits_mode_heuristic_stiched

6B • Updated May 8 • 3

inference-optimization/llama3_8b_5.5_bits_mode_noise_stiched

6B • Updated May 8 • 2

inference-optimization/llama3_8b_5.5_bits_mode_hybrid_stiched

6B • Updated May 8 • 3

inference-optimization/llama3_8b_5.5_bits_mode_heuristic_stiched

6B • Updated May 8 • 3

inference-optimization/llama3_8b_5.0_bits_mode_noise_stiched

5B • Updated May 8 • 3

inference-optimization/llama3_8b_5.0_bits_mode_hybrid_stiched

5B • Updated May 8 • 3

inference-optimization/llama3_8b_5.0_bits_mode_heuristic_stiched

5B • Updated May 8 • 4

inference-optimization/llama3_8b_6.0_bits_mode_hybrid_stiched

6B • Updated May 8 • 3

inference-optimization/qwen3-8b-peagle-speculators

inference-optimization/peagle-gemma4

2B • Updated May 6 • 4