VILA 1.5 3B
NVIDIA · dense · 3B parameters · 4,096 context
Parameters
3B
Context Window
4K tokens
Architecture
Dense
Best GPU
RTX 4070 Ti
Cheapest API
$0.08/M
Quality Score
44/100
Intelligence Brief
VILA 1.5 3B is a 3B parameter DENSE model from NVIDIA, featuring Multi-Head Attention (MHA) with 26 layers and 3,200 hidden dimensions. With a 4,096 token context window, it supports vision, multilingual. On standardized benchmarks, it achieves MMLU 50, HumanEval 22, GSM8K 42. The most cost-effective API deployment is via nvidia-nim at $0.08/M output tokens. For self-hosted inference, RTX 4070 Ti delivers optimal throughput at $237/month.
Provider pricing
1 provider · canonical: nvidia-nim| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| nvidia-nimcanonical | $0.080 | $0.080 | 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 13BVILA · 13B$0.300/M out
- VILA 1.5 40BVILA · 40B$1.00/M out
- Minitron 4BNemotron · 4B$0.060/M out
- Nemotron Mini 4BNemotron · 4B$0.060/M out
- Eagle 2.5 8BEagle · 8B—
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
6.0 GB
FP8 Weights
3.0 GB
INT4 Weights
1.5 GB
GPU Compatibility Matrix
VILA 1.5 3B is compatible with 100% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
408.2 tok/s
Latency (ITL)
2.4ms
Est. TTFT
0ms
Cost/Month
$237
Cost/M Tokens
$0.22
BF16 · 1 GPU · vllm
100/100
score
Throughput
615.6 tok/s
Latency (ITL)
1.6ms
Est. TTFT
0ms
Cost/Month
$133
Cost/M Tokens
$0.08
BF16 · 1 GPU · vllm
100/100
score
Throughput
408.2 tok/s
Latency (ITL)
2.4ms
Est. TTFT
0ms
Cost/Month
$209
Cost/M Tokens
$0.19
Deployment Options
API Deployment
nvidia-nim
$0.08/M
output tokens
Single GPU
RTX 4070 Ti
$237/mo
Min VRAM: 3 GB
Multi-GPU
RTX 4070 Ti
408.2 tok/s
Best available config
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia-nim | $0.08 | $0.08 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| nvidia-nimBest Value | $0.08 | $0.08 | $1 |
Cost per 1,000 Requests
Short (500 tok)
$0.06
via nvidia-nim
Medium (2K tok)
$0.22
via nvidia-nim
Long (8K tok)
$0.80
via nvidia-nim
Performance Estimates
Throughput by GPU
VRAM Breakdown (RTX 4070 Ti, BF16)
Precision Impact
bf16
6.0 GB
weights/GPU
~408.2 tok/s
fp8
3.0 GB
weights/GPU
int4
1.5 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy VILA 1.5 3B
Self-Hosted Infrastructure
Similar Models
OpenELM 3B
3B params · dense
Quality: 50
BTLM 3B
3B params · dense
Quality: 50
StableLM Zephyr 3B
3B params · dense
Quality: 50
Falcon 3 3B
3B params · dense
Quality: 50
StarCoder2 3B
3.03B params · dense
Quality: 29
from $0.10/M
Frequently Asked Questions
How much VRAM does VILA 1.5 3B need for inference?
VILA 1.5 3B requires approximately 6.0 GB of VRAM at BF16 precision, 3.0 GB at FP8, or 1.5 GB at INT4 quantization. Additional VRAM is needed for KV-cache (41600 bytes per token) and activations (~0.40 GB).
What is the best GPU for VILA 1.5 3B?
The top recommended GPU for VILA 1.5 3B is the RTX 4070 Ti using BF16 precision. It achieves approximately 408.2 tokens/sec at an estimated cost of $237/month ($0.22/M tokens). Score: 100/100.
How much does VILA 1.5 3B inference cost?
VILA 1.5 3B API inference starts from $0.08/M input tokens and $0.08/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.