Skip to content
Updated minutes ago
NVIDIA

Minitron 4B

NVIDIA · dense · 4B parameters · 8,192 context

Quality
50.0

Architecture Details

TypeDENSE
Total Parameters4B
Active Parameters4B
Layers32
Hidden Dimension3,072
Attention Heads24
KV Heads8
Head Dimension128
Vocab Size256,000

Memory Requirements

BF16 Weights

8.0 GB

FP8 Weights

4.0 GB

INT4 Weights

2.0 GB

KV-Cache per Token49152 bytes
Activation Estimate0.50 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

A4000optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

302.4 tok/s

Cost/Month

$161

Cost/M Tokens

$0.20

Use this config →
RTX 4080optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

483.9 tok/s

Cost/Month

$304

Cost/M Tokens

$0.24

Use this config →
RTX 4070 Tioptimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

340.2 tok/s

Cost/Month

$237

Cost/M Tokens

$0.27

Use this config →

API Pricing Comparison

ProviderInput $/MOutput $/MBadges
nvidia-nim$0.06$0.06
Cheapest

Quality Benchmarks

MMLU
56.0
HumanEval
28.0
GSM8K
55.0
MT-Bench
68.0

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

tensorrt-llmvllmsglang

Supported Precisions

BF16 (default)FP8INT4

Similar Models