Updated minutes ago
InternLM 2.5 7B
Shanghai AI Lab · dense · 7.74B parameters · 1,048,576 context
Quality50.0
Architecture Details
TypeDENSE
Total Parameters7.74B
Active Parameters7.74B
Layers32
Hidden Dimension4,096
Attention Heads32
KV Heads8
Head Dimension128
Vocab Size92,544
Memory Requirements
BF16 Weights
15.5 GB
FP8 Weights
7.7 GB
INT4 Weights
3.9 GB
KV-Cache per Token131072 bytes
Activation Estimate1.00 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
325.4 tok/s
Cost/Month
$332
Cost/M Tokens
$0.39
RTX 4090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
351.6 tok/s
Cost/Month
$370
Cost/M Tokens
$0.40
RTX 5090optimal
BF16 · 1 GPU · vllm
100/100
score
Throughput
625.1 tok/s
Cost/Month
$845
Cost/M Tokens
$0.51
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| internlm | $0.20 | $0.20 | Cheapest |
Capabilities
Features
✓ Tool Use✗ Vision✓ Code✓ Math✓ Reasoning✓ Multilingual✓ Structured Output
Supported Frameworks
vllmsglangtgiollama
Supported Precisions
BF16 (default)FP8INT4