Parameters
10B
Context Length
33K
Modality
Text
Architecture
Dense
KV Cache Rate
400 KB/tok
License
TII Falcon-LLM License 2.0
Release Date
17 Dec 2024
Knowledge Cutoff
Nov 2024
API Pricing (per 1M)
Self-hosted only
Precision
Context
Workload Memory: 10.28 GB
INT4 · 8K context
Base Weights: 4.66 GB
KV Cache: 3.13 GB
Runtime & Graphs: 2.50 GB
1x NVIDIA L4 24GB
10.3 / 21.6 GB usable
1x RTX 3060 12GB
10.3 / 10.8 GB usable
Apple M4 24GB
10.3 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 4.46.1
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
No evaluation benchmarks for Falcon3-10B available.
Overall Rank
-
Coding Rank
-
Falcon3-10B is a 10B parameter causal language model from TII engineered for advanced scientific reasoning and conversational applications. It features Grouped-Query Attention and a 32K context window for detailed long-form text analysis.
Attention
Attention Structure
Grouped-Query Attention
Attention Heads
40
Key-Value Heads
10
Attention Head Dimension
256
Position Embedding
ROPE
RoPE Theta
1,000,042
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
5,120
Number of Layers
40
FFN Intermediate Size (Dense)
23,040
Tokenizer
Vocabulary Size
131,072
The TII Falcon 3 model family comprises open-source, decoder-only language models (1B-10B parameters) designed for efficiency. Key innovations include an extended 32K token context window, Grouped-Query Attention (GQA), and specialized versions for scientific and code-oriented applications. Some variants integrate Mamba-based architectures.