Updated minutes ago
VILA 1.5 40B
NVIDIA · dense · 40B parameters · 8,192 context
Quality73.0
Architecture Details
TypeDENSE
Total Parameters40B
Active Parameters40B
Layers48
Hidden Dimension8,192
Attention Heads64
KV Heads8
Head Dimension128
Vocab Size32,000
Memory Requirements
BF16 Weights
80.0 GB
FP8 Weights
40.0 GB
INT4 Weights
20.0 GB
KV-Cache per Token196608 bytes
Activation Estimate3.00 GB
Fits on (single-node)
B200 SXM BF16B100 SXM BF16GB200 NVL72 (per GPU) BF16GB300 NVL72 (per GPU) BF16H200 SXM BF16H100 SXM FP8H100 PCIe FP8H100 NVL FP8
GPU Recommendations
H100 SXMoptimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
700.6 tok/s
Cost/Month
$1794
Cost/M Tokens
$0.97
H100 PCIeoptimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
418.3 tok/s
Cost/Month
$1794
Cost/M Tokens
$1.63
H20optimal
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
836.6 tok/s
Cost/Month
$940
Cost/M Tokens
$0.43
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia-nim | $1.00 | $1.00 | Cheapest |
Quality Benchmarks
MMLU74.0
HumanEval42.0
GSM8K78.0
MT-Bench80.0
Capabilities
Features
✗ Tool Use✓ Vision✓ Code✓ Math✗ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
tensorrt-llmvllmsglang
Supported Precisions
BF16 (default)FP8INT4