Yi-6B
Parameters
6B
Context Length
4K
Modality
Text
Architecture
Dense
KV Cache Rate
64 KB/tok
License
Apache 2.0
Release Date
2 Nov 2023
Knowledge Cutoff
Jun 2023
API Pricing (per 1M)
Self-hosted only
Hardware & System Requirements
Precision
Context
Workload Memory: 5.54 GB
INT4 · 4K context
Base Weights: 2.79 GB
KV Cache: 0.25 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
5.5 / 21.6 GB usable
1x RTX 3060 12GB
5.5 / 10.8 GB usable
Apple M4 24GB
5.5 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Runtime requirements
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 4.34.0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Architecture Diagram
Evaluation Benchmarks
No evaluation benchmarks for Yi-6B available.
Rankings
Overall Rank
-
Coding Rank
-
About Yi-6B
Yi-6B is a compact 6B parameter bilingual model developed by 01.AI for fast conversational AI, reasoning, and multilingual text processing. Released under Apache 2.0, it features Grouped-Query Attention across an extensible 200K context window.
Specifications
Attention
Attention Structure
Multi-Head Attention
Attention Heads
32
Key-Value Heads
4
Position Embedding
Absolute Position Embedding
RoPE Theta
5,000,000
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
4,096
Number of Layers
32
FFN Intermediate Size (Dense)
11,008
Tokenizer
Vocabulary Size
64,000