Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
0.0
TFLOPS
40
26
26
Xuan Son NGUYEN
ngxson
Follow
shtefcs's profile picture
fgdrfgrgrdgdr's profile picture
nezubn's profile picture
90 followers
Β·
30 following
https://blog.ngxson.com
ngxson
ngxson
ngxson
ngxson.hf.co
AI & ML interests
Doing AI for fun, not for profit
Recent Activity
reacted
to
mitkox
's
post
with π
about 7 hours ago
llama.cpp is 26.8% faster than ollama. I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison. Total duration: llama.cpp 6.85 sec <- 26.8% faster ollama 8.69 sec Breakdown by phase: Model loading llama.cpp 241 ms <- 2x faster ollama 553 ms Prompt processing llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster ollama 42.17 tokens/s with an eval time of 498 ms Token generation llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster ollama 122.07 tokens/s with an eval time 7.64 sec llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing. Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
reacted
to
mitkox
's
post
with π
about 7 hours ago
llama.cpp is 26.8% faster than ollama. I have upgraded both, and using the same settings, I am running the same DeepSeek R1 Distill 1.5B on the same hardware. It's an Apples to Apples comparison. Total duration: llama.cpp 6.85 sec <- 26.8% faster ollama 8.69 sec Breakdown by phase: Model loading llama.cpp 241 ms <- 2x faster ollama 553 ms Prompt processing llama.cpp 416.04 tokens/s with an eval time 45.67 ms <- 10x faster ollama 42.17 tokens/s with an eval time of 498 ms Token generation llama.cpp 137.79 tokens/s with an eval time 6.62 sec <- 13% faster ollama 122.07 tokens/s with an eval time 7.64 sec llama.cpp is LLM inference in C/C++; ollama adds abstraction layers and marketing. Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.
updated
a Space
1 day ago
ngxson/fastapi_hackathon_template
View all activity
Articles
Introducing GGUF-my-LoRA
Nov 1, 2024
β’
13
Code a simple RAG from scratch
Oct 29, 2024
β’
18
Introduction to ggml
Aug 13, 2024
β’
130
Organizations
ngxson
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
liked
a model
5 days ago
deepseek-ai/DeepSeek-R1
Text Generation
β’
Updated
3 days ago
β’
109k
β’
2.57k
liked
a model
11 days ago
5CD-AI/Vintern-1B-v3_5
Image-Text-to-Text
β’
Updated
8 days ago
β’
1.37k
β’
23
liked
a model
13 days ago
5CD-AI/Vintern-3B-beta
Image-Text-to-Text
β’
Updated
Dec 6, 2024
β’
962
β’
34
liked
a dataset
20 days ago
itecgo/Topical-Chat-chatml
Viewer
β’
Updated
Dec 25, 2023
β’
8.63k
β’
54
β’
1
liked
a dataset
21 days ago
vblagoje/cc_news
Viewer
β’
Updated
Jan 4, 2024
β’
708k
β’
1.05k
β’
54
liked
a model
about 1 month ago
Datou1111/shou_xin
Text-to-Image
β’
Updated
Dec 9, 2024
β’
16.3k
β’
848
liked
a Space
about 1 month ago
Running
on
CPU Upgrade
1.52k
π’
Anychat
liked
a model
3 months ago
bartowski/Qwen2.5-Coder-14B-GGUF
Text Generation
β’
Updated
Nov 11, 2024
β’
735
β’
2
liked
a Space
3 months ago
Running
1.28k
π’
Qwen2.5 Coder Artifacts
liked
a dataset
3 months ago
di-zhang-fdu/OpenLongCoT-Pretrain
Viewer
β’
Updated
Oct 28, 2024
β’
103k
β’
46
β’
87
liked
a model
3 months ago
OuteAI/OuteTTS-0.1-350M-GGUF
Text-to-Speech
β’
Updated
Nov 27, 2024
β’
211
β’
34
liked
a Space
3 months ago
Running
on
CPU Upgrade
28
π¦
GGUF My Lora
Convert your PEFT LoRA into GGUF
liked
a model
3 months ago
HuggingFaceTB/SmolLM2-1.7B-Instruct
Text Generation
β’
Updated
18 days ago
β’
85.8k
β’
β’
481
liked
a Space
3 months ago
Runtime error
451
π§ͺ
FLUX LoRa Lab
liked
2 datasets
3 months ago
reach-vb/gguf-stats
Viewer
β’
Updated
Dec 2, 2024
β’
60.5k
β’
22
β’
16
huggingface/documentation-images
Viewer
β’
Updated
1 day ago
β’
50
β’
2.56M
β’
47
liked
2 models
3 months ago
rain1011/pyramid-flow-sd3
Text-to-Video
β’
Updated
Oct 30, 2024
β’
805
bartowski/Human-Like-LLama3-8B-Instruct-GGUF
Text Generation
β’
Updated
Oct 7, 2024
β’
545
β’
2
liked
a model
4 months ago
multimodalart/vintage-ads-flux
Text-to-Image
β’
Updated
Aug 26, 2024
β’
6.25k
β’
β’
81
liked
a model
5 months ago
OuteAI/Lite-Mistral-150M-v2-Instruct-GGUF
Updated
Aug 24, 2024
β’
353
β’
13
Load more