Skip to content
Updated minutes ago
TII

Falcon 3 3B

TII UAE · dense · 3B parameters · 8,192 context

Quality
50.0

Falcon 3 3B is a 3B parameter DENSE model from TII UAE, featuring a 8,192 token context window. With 24 transformer layers and a hidden dimension of 2,560, it delivers efficient Grouped Query Attention (GQA) for optimized inference throughput. Based on InferenceBench analysis, the optimal deployment configuration is the RTX 4070 Ti at BF16 precision, achieving approximately 453.6 tokens/second at $0.20/million tokens.

Architecture Details

TypeDENSE
Total Parameters3B
Active Parameters3B
Layers24
Hidden Dimension2,560
Attention Heads20
KV Heads4
Head Dimension128
Vocab Size131,072

Memory Requirements

BF16 Weights

6.0 GB

FP8 Weights

3.0 GB

INT4 Weights

1.5 GB

KV-Cache per Token24576 bytes
Activation Estimate0.30 GB

Fits on (single-node)

B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM BF16H100 PCIe BF16H100 NVL BF16

GPU Recommendations

RTX 4070 Tioptimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

453.6 tok/s

Cost/Month

$237

Cost/M Tokens

$0.20

Use this config →
RTX 3080optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

684.0 tok/s

Cost/Month

$133

Cost/M Tokens

$0.07

Use this config →
RTX 4070 Superoptimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

453.6 tok/s

Cost/Month

$209

Cost/M Tokens

$0.18

Use this config →

API Pricing Comparison

No API pricing data available for this model.

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgillama-cppollama

Supported Precisions

BF16 (default)FP8INT4

Similar Models

Frequently Asked Questions

How much VRAM does Falcon 3 3B need for inference?

Falcon 3 3B requires approximately 6.0 GB of VRAM at BF16 precision, 3.0 GB at FP8, or 1.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (24576 bytes per token) and activations (~0.30 GB).

What is the best GPU for Falcon 3 3B?

The top recommended GPU for Falcon 3 3B is the RTX 4070 Ti using BF16 precision. It achieves approximately 453.6 tokens/sec at an estimated cost of $237/month ($0.20/M tokens). Score: 100/100.

How much does Falcon 3 3B inference cost?

Falcon 3 3B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.