Qwen2-72B

Qwen2-72B is the flagship model of the series, featuring 72 billion parameters. Its architecture includes 80 layers with a hidden size of 8192 and implements the Grouped Query Attention mechanism with 64 query heads and 8 shared key-value heads. Combined with Dual Chunk Attention and YARN technologies, this design ensures maximum performance in processing long contexts and efficient management of KV-cache memory.

The model was trained on a high-quality dataset of 7 trillion tokens, offering maximum data diversity. The base version of the model achieves outstanding results on key benchmarks: 84.2 on MMLU, 37.9 on GPQA, 64.6 on HumanEval, 89.5 on GSM8K, and 82.4 on BBH. The instruction-tuned version, Qwen2-72B-Instruct, scores 9.1 on MT-Bench, 48.1 on Arena-Hard, and 35.7 on LiveCodeBench, placing it among the top-tier proprietary models.

Qwen2-72B demonstrates exceptional capabilities in complex reasoning, step-by-step problem solving, advanced programming, and deep contextual understanding. Its multilingual support enables professional-level performance in more than 30 languages, including Russian. Accordingly, it is designed for the most demanding AI use cases—high-level scientific research, complex software development, creation of high-quality professional content, advanced data analysis, automation of complex business processes, and intelligent decision-making systems.


Announce Date: 24.07.2024
Parameters: 72B
Context: 32K
Layers: 80
Attention Type: Full Attention
VRAM requirements: 46.0 GB using 4 bits quantization
Developer: Qwen
Transformers Version: 4.40.1
License: Tongyi-Qianwen

Public endpoint

Use our pre-built public endpoints for free to test inference and explore Qwen2-72B capabilities. You can obtain an API access token on the token management page after registration and verification.
Model Name Context Type GPU TPS Status Link
There are no public endpoints for this model yet.

Private server

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

  • maximize endpoint performance,
  • enable full context for long sequences,
  • ensure top-tier security for data processing in an isolated, dedicated environment,
  • use custom weights, such as fine-tuned models or LoRA adapters.

Recommended configurations for hosting Qwen2-72B

Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
teslat4-4.16.64.160
32,768.0
16 65536 160 4 $0.96 Launch
teslaa2-4.32.128.160
32,768.0
32 131072 160 4 $1.26 Launch
teslaa10-3.16.96.160
32,768.0
16 98304 160 3 $1.34 Launch
teslav100-2.16.64.240
32,768.0
16 65535 240 2 $2.22 Launch
rtxa5000-4.16.128.160.nvlink
32,768.0
16 131072 160 4 $2.34 Launch
rtx3090-3.16.96.160
32,768.0
16 98304 160 3 $2.45 Launch
teslaa100-1.16.64.160
32,768.0
16 65536 160 1 $2.58 Launch
rtx5090-2.16.64.160
32,768.0
16 65536 160 2 $2.93 Launch
rtx4090-3.16.96.160
32,768.0
16 98304 160 3 $3.23 Launch
teslah100-1.16.64.160
32,768.0
16 65536 160 1 $5.11 Launch
h200-1.16.128.160
32,768.0
16 131072 160 1 $6.98 Launch
Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
rtxa5000-6.24.192.160.nvlink
32,768.0
24 196608 160 6 $3.50 Launch
teslav100-3.64.256.320
32,768.0
64 262144 320 3 $3.89 Launch
rtx5090-3.16.96.160
32,768.0
16 98304 160 3 $4.34 Launch
teslaa100-2.24.96.160.nvlink
32,768.0
24 98304 160 2 $5.04 Launch
rtx4090-6.44.256.160
32,768.0
44 262144 160 6 $6.63 Launch
h200-1.16.128.160
32,768.0
16 131072 160 1 $6.98 Launch
teslah100-2.24.256.160
32,768.0
24 262144 160 2 $10.40 Launch
Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
teslaa100-3.32.384.240
32,768.0
32 393216 240 3 $8.00 Launch
rtx5090-6.44.256.240
32,768.0
44 262144 240 6 $8.86 Launch
h200-2.24.256.240
32,768.0
24 262144 240 2 $13.89 Launch
teslah100-3.32.384.240
32,768.0
32 393216 240 3 $15.58 Launch

Related models

QwQ

Need help?

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.