VILA 1.5 13B
NVIDIA · dense · 13B parameters · 4,096 context
Parameters
13B
Context Window
4K tokens
Architecture
Dense
Best GPU
A100 40GB SXM
Cheapest API
$0.30/M
Quality Score
62/100
Intelligence Brief
VILA 1.5 13B is a 13B parameter DENSE model from NVIDIA, featuring Grouped Query Attention (GQA) with 40 layers and 5,120 hidden dimensions. With a 4,096 token context window, it supports vision, structured output, code, math, multilingual. On standardized benchmarks, it achieves MMLU 65, HumanEval 34, GSM8K 64. The most cost-effective API deployment is via nvidia-nim at $0.30/M output tokens. For self-hosted inference, A100 40GB SXM delivers optimal throughput at $807/month.
Provider pricing
1 provider · canonical: nvidia-nim| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| nvidia-nimcanonical | $0.300 | $0.300 | cheapest input · cheapest output |
Prices update via the nightly pricing cron + admin approvals at /admin/ingest-queue. The leaderboard's Input/Output cells show the canonical rate above; this table shows the full spread.
Recent changes
Loading…
Related models
5 suggestions- VILA 1.5 3BVILA · 3B$0.080/M out
- VILA 1.5 40BVILA · 40B$1.00/M out
- Alpamayo 1.5-10BAlpamayo · 10B—
- Cosmos 7BCosmos · 7B—
- Eagle 2 9BEagle · 9B—
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
26.0 GB
FP8 Weights
13.0 GB
INT4 Weights
6.5 GB
GPU Compatibility Matrix
VILA 1.5 13B is compatible with 82% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
95/100
score
Throughput
322.9 tok/s
Latency (ITL)
3.1ms
Est. TTFT
1ms
Cost/Month
$807
Cost/M Tokens
$0.95
BF16 · 1 GPU · vllm
95/100
score
Throughput
159.5 tok/s
Latency (ITL)
6.3ms
Est. TTFT
1ms
Cost/Month
$465
Cost/M Tokens
$1.11
BF16 · 1 GPU · vllm
95/100
score
Throughput
144.5 tok/s
Latency (ITL)
6.9ms
Est. TTFT
1ms
Cost/Month
$399
Cost/M Tokens
$1.05
Deployment Options
API Deployment
nvidia-nim
$0.30/M
output tokens
Single GPU
A100 40GB SXM
$807/mo
Min VRAM: 13 GB
Multi-GPU
RTX 3090 x2
319.5 tok/s
TP· $361/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia-nim | $0.30 | $0.30 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| nvidia-nimBest Value | $0.30 | $0.30 | $3 |
Cost per 1,000 Requests
Short (500 tok)
$0.21
via nvidia-nim
Medium (2K tok)
$0.84
via nvidia-nim
Long (8K tok)
$3.00
via nvidia-nim
Performance Estimates
Throughput by GPU
VRAM Breakdown (A100 40GB SXM, BF16)
Precision Impact
bf16
26.0 GB
weights/GPU
~322.9 tok/s
fp8
13.0 GB
weights/GPU
int4
6.5 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy VILA 1.5 13B
Similar Models
OLMo 2 13B
13B params · dense
Quality: 50
Baichuan 2 13B
13B params · dense
Quality: 50
from $0.25/M
Cerebras GPT 13B
13B params · dense
Quality: 50
ELYZA 13B
13B params · dense
Quality: 50
Vicuna 13B
13B params · dense
Quality: 50
Frequently Asked Questions
How much VRAM does VILA 1.5 13B need for inference?
VILA 1.5 13B requires approximately 26.0 GB of VRAM at BF16 precision, 13.0 GB at FP8, or 6.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (102400 bytes per token) and activations (~1.20 GB).
What is the best GPU for VILA 1.5 13B?
The top recommended GPU for VILA 1.5 13B is the A100 40GB SXM using BF16 precision. It achieves approximately 322.9 tokens/sec at an estimated cost of $807/month ($0.95/M tokens). Score: 95/100.
How much does VILA 1.5 13B inference cost?
VILA 1.5 13B API inference starts from $0.30/M input tokens and $0.30/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.