Falcon 7B
TII · dense · 7B parameters · 2,048 context
Parameters
7B
Context Window
2K tokens
Architecture
Dense
Best GPU
A10G
Cheapest API
$0.15/M
Quality Score
37/100
Intelligence Brief
Falcon 7B is a 7B parameter DENSE model from TII, featuring Grouped Query Attention (GQA) with 32 layers and 4,544 hidden dimensions. With a 2,048 token context window, it supports code, multilingual. On standardized benchmarks, it achieves MMLU 44.7, HumanEval 18, GSM8K 30. The most cost-effective API deployment is via tii at $0.15/M output tokens. For self-hosted inference, A10G delivers optimal throughput at $285/month.
Architecture Details
Memory Requirements
BF16 Weights
14.0 GB
FP8 Weights
7.0 GB
INT4 Weights
3.5 GB
GPU Compatibility Matrix
Falcon 7B is compatible with 95% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
219.8 tok/s
Latency (ITL)
4.5ms
Est. TTFT
1ms
Cost/Month
$285
Cost/M Tokens
$0.49
BF16 · 1 GPU · vllm
100/100
score
Throughput
341.9 tok/s
Latency (ITL)
2.9ms
Est. TTFT
0ms
Cost/Month
$332
Cost/M Tokens
$0.37
BF16 · 1 GPU · vllm
100/100
score
Throughput
369.3 tok/s
Latency (ITL)
2.7ms
Est. TTFT
0ms
Cost/Month
$370
Cost/M Tokens
$0.38
Deployment Options
API Deployment
tii
$0.15/M
output tokens
Single GPU
A10G
$285/mo
Min VRAM: 7 GB
Multi-GPU
RTX 3080 x2
430.0 tok/s
TP· $266/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| tii | $0.15 | $0.15 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| tiiBest Value | $0.15 | $0.15 | $2 |
Cost per 1,000 Requests
Short (500 tok)
$0.10
via tii
Medium (2K tok)
$0.42
via tii
Long (8K tok)
$1.50
via tii
Performance Estimates
Throughput by GPU
VRAM Breakdown (A10G, BF16)
Precision Impact
bf16
14.0 GB
weights/GPU
~219.8 tok/s
fp8
7.0 GB
weights/GPU
int4
3.5 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Falcon 7B
Self-Hosted Infrastructure
Similar Models
Falcon 3 7B
7.5B params · dense
Quality: 50
Falcon 3 10B
10.3B params · dense
Quality: 50
Falcon 11B
11B params · dense
Quality: 50
Falcon 3 3B
3B params · dense
Quality: 50
OLMo 2 7B
7B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does Falcon 7B need for inference?
Falcon 7B requires approximately 14.0 GB of VRAM at BF16 precision, 7.0 GB at FP8, or 3.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (8192 bytes per token) and activations (~0.50 GB).
What is the best GPU for Falcon 7B?
The top recommended GPU for Falcon 7B is the A10G using BF16 precision. It achieves approximately 219.8 tokens/sec at an estimated cost of $285/month ($0.49/M tokens). Score: 100/100.
How much does Falcon 7B inference cost?
Falcon 7B API inference starts from $0.15/M input tokens and $0.15/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.