Updated minutes ago
VILA 1.5 3B
NVIDIA · dense · 3B parameters · 4,096 context
Quality44.0
Architecture Details
TypeDENSE
Total Parameters3B
Active Parameters3B
Layers26
Hidden Dimension3,200
Attention Heads32
KV Heads32
Head Dimension100
Vocab Size32,000
Memory Requirements
BF16 Weights
6.0 GB
FP8 Weights
3.0 GB
INT4 Weights
1.5 GB
KV-Cache per Token41600 bytes
Activation Estimate0.40 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
408.2 tok/s
Cost/Month
$237
Cost/M Tokens
$0.22
RTX 3080optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
615.6 tok/s
Cost/Month
$133
Cost/M Tokens
$0.08
RTX 4070 Superoptimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
408.2 tok/s
Cost/Month
$209
Cost/M Tokens
$0.19
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia-nim | $0.08 | $0.08 | Cheapest |
Quality Benchmarks
MMLU50.0
HumanEval22.0
GSM8K42.0
MT-Bench65.0
Capabilities
Features
✗ Tool Use✓ Vision✗ Code✗ Math✗ Reasoning✓ Multilingual✗ Structured Output
Supported Frameworks
tensorrt-llmvllmsglang
Supported Precisions
BF16 (default)FP8INT4