Falcon-180B
Parameters
180B
Context Length
2K
Modality
Text
Architecture
Dense
KV Cache Rate
30 KB/tok
License
Falcon-180B TII License and Acceptable Use Policy
Release Date
23 Sept 2023
Knowledge Cutoff
Dec 2022
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Context
Workload Memory: 337.83 GB
FP16 · 2048 context
Base Weights: 335.28 GB
KV Cache: 0.06 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
8x NVIDIA H100 80GB
337.8 / 576.0 GB usable · TP 8
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
Evaluation Benchmarks
Rank
#237
| Benchmark | Score | Rank |
|---|---|---|
General Text | 1148 | 190 |
Rankings
Overall Rank
#237
Coding Rank
-
About Falcon-180B
Falcon-180B is TII's 180B parameter flagship causal language model pretrained on 3.5T tokens for advanced reasoning, research, and coding. It utilizes Multi-Query Attention and custom 3D parallelism for high-scale enterprise deployments.
Technical Specifications
Attention
Attention Structure
Multi-Query Attention
Attention Heads
96
Key-Value Heads
1
Position Embedding
ROPE
Normalization
Layer Normalization
Activation Function
GELU
Dimensions
Hidden Dimension Size
12,288
Number of Layers
60
About Falcon
The TII Falcon model family comprises causal decoder-only language models (7B, 40B). Their architecture, adapted from GPT-3, integrates rotary positional embeddings, Multi-Query Attention for inference efficiency, and FlashAttention for accelerated operations. Models are trained on the RefinedWeb dataset.