← All Models
|
Qwen - Alibaba Cloud's multilingual LLM series:
Qwen1.5-0.5B
Qwen1.5-1.8B
Qwen1.5-4B
Qwen1.5-7B
Qwen1.5-14B
Qwen1.5-32B
Qwen1.5-72B
Qwen1.5-110B
Qwen1.5-MoE-A2.7B
Qwen2-0.5B
Qwen2-1.5B
Qwen2-7B
Qwen2-57B-A14B
Qwen2-72B
Qwen2.5-0.5B
Qwen2.5-1.5B
Qwen2.5-3B
Qwen2.5-7B
Qwen2.5-14B
Qwen2.5-32B
Qwen2.5-72B
Qwen3-0.6B
Qwen3-1.7B
Qwen3-4B
Qwen3-8B
Qwen3-14B
Qwen3-32B
Qwen3-30B-A3B
Qwen3-235B-A22B
Qwen/Qwen3-32B
📊 Model Parameters
Total Parameters
32,762,123,264
Context Length
40,960
Hidden Size
5120
Layers
64
Attention Heads
64
KV Heads
8
💾 Memory Requirements
FP32 (Full)
122.05 GB
FP16 (Half)
61.02 GB
INT8 (Quantized)
30.51 GB
INT4 (Quantized)
15.26 GB
🔑 KV Cache (Inference)
Per Token (FP16)
262.14 KB
Max Context FP32
20.00 GB
Max Context FP16
10.00 GB
Max Context INT8
5.00 GB
⚙️ Model Configuration
Core Architecture
Vocabulary Size
151,936
Hidden Size
5,120
FFN Intermediate Size
25,600
Number of Layers
64
Attention Heads
64
KV Heads
8
Head Dimension
128
Context & Position
Max Context Length
40,960
Uses Sliding Window
No
Sliding Window Size
Not set
Window Attention Layers
64
RoPE Base Frequency
1,000,000
RoPE Scaling
Not set
Layer Attention Types
[64 items]
Attention Configuration
Attention Bias
No
Attention Dropout
0%
Tied Embeddings
No
Activation & Normalization
Activation Function
silu
RMSNorm Epsilon
1e-06
Special Tokens
BOS Token ID
151,643
Pad Token ID
Not set
EOS Token ID
151645
Data Type
Model Dtype
bfloat16
Layer Types:
Attention
MLP/FFN
Normalization
Embedding
Attention
MLP
Norm
Embedding
Clear
Expand All
Collapse All