Hugging Face's logo
Steve Li's picture
TFLOPS icon 29.1 TFLOPS
43 10

Steve Li

CHNtentes
21world's profile picture ltim's profile picture
·

AI & ML interests

None yet

Recent Activity

New activity 3 days ago
NexaAIDev/omnivision-968M
New activity 16 days ago
city96/stable-diffusion-3.5-medium-gguf
New activity 19 days ago
stabilityai/stable-diffusion-3.5-medium

Organizations

None yet

CHNtentes's activity

New activity in NexaAIDev/omnivision-968M 3 days ago

transformers version?

1
#5 opened 3 days ago by CHNtentes
New activity in city96/stable-diffusion-3.5-medium-gguf 16 days ago

Q4_0, Q4_1, Q5_0, Q5_1 can be dropped?

1
#1 opened 16 days ago by CHNtentes
New activity in stabilityai/stable-diffusion-3.5-medium 19 days ago

Where is 't5xxl.safetensors' ?

4
#12 opened 20 days ago by ajavamind
New activity in ArtificialAnalysis/Text-to-Image-Leaderboard 24 days ago

🐼🐼🐼

2
#3 opened 24 days ago by clem
New activity in Qwen/Qwen2-VL-2B-Instruct about 2 months ago

Hardware requirements

4
#10 opened 2 months ago by ZahirHamroune
New activity in stepfun-ai/GOT-OCR2_0 2 months ago

T4 - bfloat 16 not support

10
#2 opened 2 months ago by SylvainV
New activity in mattshumer/Reflection-Llama-3.1-70B 2 months ago

🚩 Report: Spam
#150 opened 2 months ago by CHNtentes
New activity in city96/FLUX.1-dev-gguf 3 months ago

Is it using ggml to compute?

1
#30 opened 3 months ago by CHNtentes
New activity in city96/t5-v1_1-xxl-encoder-gguf 3 months ago

For the fastest inference on 12GB VRAM, are the following GGUF models appropriate to use?

3
#4 opened 3 months ago by ViratX
New activity in google/gemma-2-9b-it 3 months ago

Inquiry on Minimum Configuration and Cost for Running Gemma-2-9B Model Efficiently

3
#39 opened 3 months ago by ltkien2003
New activity in nvidia/Llama-3.1-Minitron-4B-Width-Base 3 months ago

Error in readme?

1
#6 opened 3 months ago by CHNtentes
New activity in alvdansen/flux-koda 3 months ago

Good work!

1
#1 opened 3 months ago by CHNtentes
New activity in city96/FLUX.1-dev-gguf 3 months ago

Compared to the regular FP8 model, what is the better performance of the 8BIT model here

4
#16 opened 3 months ago by demo001s

Please explain the difference between the two models

3
#11 opened 3 months ago by martjay

k-quants possible?

5
#2 opened 3 months ago by CHNtentes
New activity in black-forest-labs/FLUX.1-dev 3 months ago

weight dtype "default" very slow

3
#44 opened 4 months ago by D3NN15
New activity in black-forest-labs/FLUX.1-dev 4 months ago

How do you get this to work?

7
#36 opened 4 months ago by BirdPerson22

HELP!

7
#34 opened 4 months ago by Seltic

max resolution?

4
#32 opened 4 months ago by CHNtentes

Why 12b? Who could run that locally?

47
#1 opened 4 months ago by kaidu88