Skip to content
Updated minutes ago
InternLM

InternLM3 8B

Shanghai AI Lab · dense · 8B parameters · 32,768 context

Quality
50.0

InternLM3 8B is a 8B parameter DENSE model from Shanghai AI Lab, featuring a 32,768 token context window. With 32 transformer layers and a hidden dimension of 4,096, it delivers efficient Grouped Query Attention (GQA) for optimized inference throughput. Based on InferenceBench analysis, the optimal deployment configuration is the A30 at BF16 precision, achieving approximately 314.9 tokens/second at $0.40/million tokens.

Architecture Details

TypeDENSE
Total Parameters8B
Active Parameters8B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size103,168

Memory Requirements

BF16 Weights

16.0 GB

FP8 Weights

8.0 GB

INT4 Weights

4.0 GB

KV-Cache per Token65536 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

A30optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

314.9 tok/s

Cost/Month

$332

Cost/M Tokens

$0.40

Use this config →
RTX 4090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

340.2 tok/s

Cost/Month

$370

Cost/M Tokens

$0.41

Use this config →
RTX 3090optimal

BF16 · 1 GPU · vllm

100/100

score

Throughput

315.9 tok/s

Cost/Month

$180

Cost/M Tokens

$0.22

Use this config →

API Pricing Comparison

No API pricing data available for this model.

Capabilities

Features

Tool Use Vision Code Math Reasoning Multilingual Structured Output

Supported Frameworks

vllmsglangtgillama-cpp

Supported Precisions

BF16 (default)FP8INT4

Similar Models

Frequently Asked Questions

How much VRAM does InternLM3 8B need for inference?

InternLM3 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 (~0.50 GB).

What is the best GPU for InternLM3 8B?

The top recommended GPU for InternLM3 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 InternLM3 8B inference cost?

InternLM3 8B inference costs vary by provider and GPU setup. Use our calculator for detailed cost estimates across all providers.