Updated minutes ago
Falcon 7B
TII · dense · 7B parameters · 2,048 context
Quality37.0
Architecture Details
TypeDENSE
Total Parameters7B
Active Parameters7B
Layers32
Hidden Dimension4,544
Attention Heads71
KV Heads1
Head Dimension64
Vocab Size65,024
Memory Requirements
BF16 Weights
14.0 GB
FP8 Weights
7.0 GB
INT4 Weights
3.5 GB
KV-Cache per Token8192 bytes
Activation Estimate0.50 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
A10Goptimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
219.8 tok/s
Cost/Month
$285
Cost/M Tokens
$0.49
A30optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
341.9 tok/s
Cost/Month
$332
Cost/M Tokens
$0.37
RTX 4090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
369.3 tok/s
Cost/Month
$370
Cost/M Tokens
$0.38
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| tii | $0.15 | $0.15 | Cheapest |
Quality Benchmarks
MMLU44.7
HumanEval18.0
GSM8K30.0
MT-Bench60.0
Capabilities
Features
✗ Tool Use✗ Vision✓ Code✗ Math✗ Reasoning✓ Multilingual✗ Structured Output
Supported Frameworks
vllmsglangtgitensorrt-llmollama
Supported Precisions
BF16 (default)FP8INT4