Minitron 8B
NVIDIA · dense · 8B parameters · 8,192 context
Parameters
8B
Context Window
8K tokens
Architecture
Dense
Best GPU
A30
Cheapest API
$0.10/M
Quality Score
62/100
Intelligence Brief
Minitron 8B is a 8B parameter DENSE model from NVIDIA, featuring Grouped Query Attention (GQA) with 32 layers and 4,096 hidden dimensions. With a 8,192 token context window, it supports tools, structured output, code, math, multilingual. On standardized benchmarks, it achieves MMLU 65, HumanEval 36, GSM8K 68. The most cost-effective API deployment is via nvidia-nim at $0.10/M output tokens. For self-hosted inference, A30 delivers optimal throughput at $332/month.
Architecture Details
Memory Requirements
BF16 Weights
16.0 GB
FP8 Weights
8.0 GB
INT4 Weights
4.0 GB
GPU Compatibility Matrix
Minitron 8B is compatible with 90% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
BF16 · 1 GPU · vllm
100/100
score
Throughput
314.9 tok/s
Latency (ITL)
3.2ms
Est. TTFT
1ms
Cost/Month
$332
Cost/M Tokens
$0.40
BF16 · 1 GPU · vllm
100/100
score
Throughput
340.2 tok/s
Latency (ITL)
2.9ms
Est. TTFT
1ms
Cost/Month
$370
Cost/M Tokens
$0.41
BF16 · 1 GPU · vllm
100/100
score
Throughput
315.9 tok/s
Latency (ITL)
3.2ms
Est. TTFT
1ms
Cost/Month
$180
Cost/M Tokens
$0.22
Deployment Options
API Deployment
nvidia-nim
$0.10/M
output tokens
Single GPU
A30
$332/mo
Min VRAM: 8 GB
Multi-GPU
RTX 3060 x2
190.4 tok/s
TP· $114/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| nvidia-nim | $0.10 | $0.10 | Cheapest |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| nvidia-nimBest Value | $0.10 | $0.10 | $1 |
Cost per 1,000 Requests
Short (500 tok)
$0.07
via nvidia-nim
Medium (2K tok)
$0.28
via nvidia-nim
Long (8K tok)
$1.00
via nvidia-nim
Performance Estimates
Throughput by GPU
VRAM Breakdown (A30, BF16)
Precision Impact
bf16
16.0 GB
weights/GPU
~314.9 tok/s
fp8
8.0 GB
weights/GPU
int4
4.0 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy Minitron 8B
Self-Hosted Infrastructure
Similar Models
Minitron 4B
4B params · dense
Quality: 50
from $0.06/M
Nemotron Mini 4B
4B params · dense
Quality: 48
from $0.06/M
Nemotron 15B
15B params · dense
Quality: 72
from $0.30/M
Aya 23 8B
8B params · dense
Quality: 50
from $0.60/M
DeepSeek R1 Distill 8B
8B params · dense
Quality: 88
from $0.20/M
Frequently Asked Questions
How much VRAM does Minitron 8B need for inference?
Minitron 8B requires approximately 16.0 GB of VRAM at BF16 precision, 8.0 GB at FP8, or 4.0 GB at INT4 quantization. Additional VRAM is needed for KV-cache (65536 bytes per token) and activations (~0.80 GB).
What is the best GPU for Minitron 8B?
The top recommended GPU for Minitron 8B is the A30 using BF16 precision. It achieves approximately 314.9 tokens/sec at an estimated cost of $332/month ($0.40/M tokens). Score: 100/100.
How much does Minitron 8B inference cost?
Minitron 8B API inference starts from $0.10/M input tokens and $0.10/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.