Falcon 3 1B
TII UAE · dense · 1B parameters · 8,192 context
Falcon 3 1B is a 1B parameter DENSE model from TII UAE, featuring a 8,192 token context window. With 18 transformer layers and a hidden dimension of 2,048, it delivers efficient Grouped Query Attention (GQA) for optimized inference throughput. Based on InferenceBench analysis, the optimal deployment configuration is the RTX 3080 at BF16 precision, achieving approximately 2.1K tokens/second at $0.02/million tokens.
Architecture Details
Memory Requirements
BF16 Weights
2.0 GB
FP8 Weights
1.0 GB
INT4 Weights
0.5 GB
Fits on (single-node)
GPU Recommendations
BF16 · 1 GPU · vllm
90/100
score
Throughput
2.1K tok/s
Cost/Month
$133
Cost/M Tokens
$0.02
BF16 · 1 GPU · vllm
90/100
score
Throughput
734.4 tok/s
Cost/Month
$209
Cost/M Tokens
$0.11
BF16 · 1 GPU · vllm
90/100
score
Throughput
1.2K tok/s
Cost/Month
$85
Cost/M Tokens
$0.03
API Pricing Comparison
No API pricing data available for this model.
Capabilities
Features
Supported Frameworks
Supported Precisions
Similar Models
Frequently Asked Questions
How much VRAM does Falcon 3 1B need for inference?
Falcon 3 1B requires approximately 2.0 GB of VRAM at BF16 precision, 1.0 GB at FP8, or 0.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (18432 bytes per token) and activations (~0.20 GB).
What is the best GPU for Falcon 3 1B?
The top recommended GPU for Falcon 3 1B is the RTX 3080 using BF16 precision. It achieves approximately 2.1K tokens/sec at an estimated cost of $133/month ($0.02/M tokens). Score: 90/100.
How much does Falcon 3 1B inference cost?
Falcon 3 1B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.