Haihao Shen

Haihao's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented a paper 4 months ago

SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Paper • 2512.04746 • Published Dec 4, 2025 • 14 •

2

New activity in Intel/GLM-4.6-REAP-218B-A32B-FP8-gguf-q2ks-mixed-AutoRound 4 months ago

auto round version plz

2

#1 opened 4 months ago by

twhitworth

New activity in Intel/Mistral-Small-3.2-24B-Instruct-2506-int4-AutoRound 5 months ago

Could you please do Magistral next?

3

#2 opened 5 months ago by

tasticleeze

New activity in Intel/Qwen3-Next-80B-A3B-Thinking-int4-mixed-AutoRound 6 months ago

CPU only?

4

#2 opened 6 months ago by

jujutechnology

New activity in Intel/Qwen3-Next-80B-A3B-Thinking-int4-AutoRound 6 months ago

Difference between int4-mixed and int4

1

#1 opened 6 months ago by

whoisjeremylam

New activity in Intel/Qwen3-Coder-30B-A3B-Instruct-gguf-q2ks-mixed-AutoRound 8 months ago

Can't wait to see the benchmark

🤝 1

16

#1 opened 8 months ago by

PussyHut

New activity in Intel/Qwen3-Coder-30B-A3B-Instruct-gguf-q4km-AutoRound 8 months ago

Scored 68.57 on MMLU Pro single shot using llama.cpp

🚀 1

3

#2 opened 8 months ago by

xbruce22

Scored 64.29 4bit on MMLU Pro single shot using ollama

4

#1 opened 8 months ago by

xbruce22

New activity in Intel/Qwen3-Coder-30B-A3B-Instruct-gguf-q2ks-mixed-AutoRound 8 months ago

Scored 65.00 on MMLU Pro single shot 🔥

❤️🔥 2

3

#2 opened 8 months ago by

xbruce22

New activity in Intel/Qwen3-30B-A3B-Instruct-2507-gguf-q2ks-mixed-AutoRound 8 months ago

this looks really good on llama.cpp

🚀 1

6

#1 opened 8 months ago by

gopi87

New activity in Qwen/Qwen3-30B-A3B-Instruct-2507 8 months ago

AWQ version

❤️ 6

6

#3 opened 8 months ago by

devops724

commented a paper over 1 year ago

A dynamic parallel method for performance optimization on hybrid CPUs

Paper • 2411.19542 • Published Nov 29, 2024 • 5 •

2

New activity in Intel/neural-chat-7b-v3 over 1 year ago

Adding `safetensors` variant of this model

#9 opened over 1 year ago by

SFconvertbot

New activity in Intel/neural-chat-7b-v3-3 over 1 year ago

Adding `safetensors` variant of this model

1

#14 opened over 1 year ago by

SFconvertbot

commented a paper about 2 years ago

Efficient Post-training Quantization with FP8 Formats

Paper • 2309.14592 • Published Sep 26, 2023 • 11 •

2

commented a paper over 2 years ago

Effective Quantization for Diffusion Models on CPUs

Paper • 2311.16133 • Published Nov 2, 2023 • 4 •

1

New activity in Intel/neural-chat-7b-v3-1 over 2 years ago

Prompt Template?

👍 4

13

#1 opened over 2 years ago by

fakezeta

commented a paper over 2 years ago

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

Paper • 2309.05516 • Published Sep 11, 2023 • 11 •

2