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
Attention Type: Full Attention
VRAM requirements: 43.5 GB using 4 bits quantization
Developer: Alibaba
Transformers Version: 4.40.1
License: Tongyi-Qianwen

Public endpoint

Use our pre-built public endpoints to test inference and explore Qwen2-72B capabilities.
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
teslaa10-2.16.64.160 16 65536 160 2 $0.93 Launch
teslat4-4.16.64.160 16 65536 160 4 $1.48 Launch
rtx3090-2.16.64.160 16 65536 160 2 $1.67 Launch
rtx4090-2.16.64.160 16 65536 160 2 $2.19 Launch
teslav100-2.16.64.240 16 65535 240 2 $2.22 Launch
teslaa100-1.16.64.160 16 65536 160 1 $2.58 Launch
rtx5090-2.16.64.160 16 65536 160 2 $2.93 Launch
teslah100-1.16.64.160 16 65536 160 1 $5.11 Launch
Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
teslaa10-4.16.128.160 16 131072 160 4 $1.75 Launch
rtx3090-4.16.128.160 16 131072 160 4 $3.23 Launch
rtx4090-4.16.128.160 16 131072 160 4 $4.26 Launch
rtx5090-3.16.96.160 16 98304 160 3 $4.34 Launch
teslaa100-2.24.256.160 24 262144 160 2 $5.35 Launch
teslah100-2.24.256.160 24 262144 160 2 $10.40 Launch
Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
teslaa100-2.24.256.240 24 262144 240 2 $5.36 Launch
teslah100-2.24.256.240 24 262144 240 2 $10.41 Launch

Related models

QwQ
Qwen2-0.5B
Qwen2-1.5B
Qwen2-7B
Qwen2.5-0.5B
Qwen2.5-1.5B
Qwen2.5-3B
Qwen2.5-7B
Qwen2.5-14B
Qwen2.5-32B
Qwen2.5-72B
Qwen2-57B-A14B
DeepSeek-R1-Distill-Qwen-32B
DeepSeek-R1-Distill-Qwen-1.5B
Qwen2.5-VL-3B
Qwen2.5-VL-7B
Qwen2.5-7B-1M

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.