AIBase
EN

AI News

View More

Large models can also fit in your pocket! Google will launch the Coral AI development board this summer, unlocking offline real-time voice translation

16.1k 11 hours ago
Large models can also fit in your pocket! Google will launch the Coral AI development board this summer, unlocking offline real-time voice translation

Ending the Performance Black Box: Windows 11 Task Manager Now Officially Supports NPU Monitoring

13.2k yesterday
Ending the Performance Black Box: Windows 11 Task Manager Now Officially Supports NPU Monitoring

Microsoft strongly promotes NPU, but consumers find it hard to find a reason to buy

9.7k 3 days ago
Microsoft strongly promotes NPU, but consumers find it hard to find a reason to buy

Intel Establishes AI PC Experience Development Centers in Indian Universities

12.2k 2 days ago
Intel Establishes AI PC Experience Development Centers in Indian Universities

Models

View More

Doubao-1.5-pro-32k

Bytedance

Doubao-1.5-pro-32k

$0.8

Input tokens/M

$2

Output tokens/M

128

Context Length

Doubao-Seed-1.6-flash

Bytedance

Doubao-Seed-1.6-flash

$0.15

Input tokens/M

$1.5

Output tokens/M

256

Context Length

Qwen3-1.7B

Alibaba

Qwen3-1.7B

-

Input tokens/M

-

Output tokens/M

32

Context Length

GPT OSS 120B

Openai

GPT OSS 120B

$0.63

Input tokens/M

$3.15

Output tokens/M

131

Context Length

Hunyuan-Translation-Lite

Tencent

Hunyuan-Translation-Lite

$1

Input tokens/M

$3

Output tokens/M

4

Context Length

Gemma 3 4B

Google

Gemma 3 4B

$0.14

Input tokens/M

$0.28

Output tokens/M

131

Context Length

Gemma 3 12B

Google

Gemma 3 12B

$0.35

Input tokens/M

$0.7

Output tokens/M

131

Context Length

Gemma 3 27B

Google

Gemma 3 27B

$0.7

Input tokens/M

$1.4

Output tokens/M

131

Context Length

Gemma 3 1B

Google

Gemma 3 1B

-

Input tokens/M

-

Output tokens/M

-

Context Length

DeepSeek-R1-Distill-Llama-8B

Deepseek

DeepSeek-R1-Distill-Llama-8B

$1

Input tokens/M

-

Output tokens/M

8

Context Length

Qwen_v2.5_7b_base

Alibaba

Qwen_v2.5_7b_base

$2

Input tokens/M

-

Output tokens/M

128

Context Length

GLM-Z1-Air

Chatglm

GLM-Z1-Air

-

Input tokens/M

-

Output tokens/M

128

Context Length

Qwen_v2.5_3b_base

Alibaba

Qwen_v2.5_3b_base

$2

Input tokens/M

-

Output tokens/M

32

Context Length

CogVideoX-2

Chatglm

CogVideoX-2

-

Input tokens/M

-

Output tokens/M

-

Context Length

ERNIE-4.5-VL-28B-A3B

Baidu

ERNIE-4.5-VL-28B-A3B

$1

Input tokens/M

$10

Output tokens/M

32

Context Length

Gemma 2 27B

Google

Gemma 2 27B

-

Input tokens/M

-

Output tokens/M

-

Context Length

Llama 3.1 8B Onnx Ryzenai Npu

amd

L

Llama-3.1-8B-onnx-ryzenai-npu is an optimized version developed by AMD based on Meta's Llama-3.1-8B model, specifically optimized for deployment on the AMD Ryzen AI NPU. Through Quark quantization, OGA model builder, and NPU-specific post-processing technology, this model significantly improves the inference efficiency on AMD hardware while maintaining high-quality text generation capabilities.

Natural Language ProcessingOnnxOnnxEnglish
amd
124
1

Llama 3 8B Awq G128 Int4 Asym Bf16 Onnx Ryzen Strix

amd

L

This project is based on the Meta-Llama-3-8B model, using Quark quantization technology, combined with the OGA model builder, and post-processed to adapt to NPU deployment. It can be used for text generation tasks. This model is specially optimized for AMD NPU hardware and supports efficient inference deployment.

Natural Language ProcessingOnnxOnnxEnglish
amd
182
2