Parameters
27B
Context Length
262K
Modality
Text
Architecture
Dense
KV Cache Rate
256 KB/tok
License
Apache 2.0
Release Date
1 Oct 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Self-hosted only
Precision
Context
Workload Memory: 17.07 GB
INT4 · 8K context
Base Weights: 12.57 GB
KV Cache: 2.00 GB
Runtime & Graphs: 2.50 GB
1x NVIDIA L4 24GB
17.1 / 21.6 GB usable
2x RTX 4090 24GB
17.1 / 43.2 GB usable · TP 2
Apple M4 24GB
17.1 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 5.17.0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
No evaluation benchmarks for PPLX Decider v1 27B available.
Overall Rank
-
Coding Rank
-
pplx-decider-v1-27B is a 27-billion parameter router and decision model created by Perplexity AI based on the Qwen architecture. It is specialized in routing search queries, intent classification, and verification pipelines.
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
24
Key-Value Heads
4
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
10,000,000
Linear Attention
Yes
Linear Attention Ratio
75.0%
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
5,120
Number of Layers
64
FFN Intermediate Size (Dense)
17,408
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
248,320
The pplx-decider model family developed by Perplexity.