GLM-4-32B-Base-0414 is a base model with 32 billion parameters from the new GLM-4–0414 series developed by Team GLM. It was trained on 15TB of high-quality data, including a significant amount of synthetic materials focused on logical reasoning. This training enables a solid foundation for subsequent reinforcement learning and adaptation to user preferences.
The model was developed under the "all tools" concept, allowing it to efficiently interact with external resources such as Python, web search, user APIs, and other services. Thanks to this capability, it demonstrates excellent performance in handling complex agent-like tasks, including code generation, function calling, information retrieval, and report creation.
Its performance is comparable to industry leaders like GPT-4o and DeepSeek-V3-0324 (671B), especially in programming tasks. The model is capable of generating over 500 lines of functional code in various programming languages without additional prompts. It supports a context length of up to 128K tokens (using YaRN, with a base of 32K) and offers convenient local deployment, making it a versatile solution for enterprise applications where result predictability and stability are critical.
| Model Name | Context | Type | GPU | Status | Link |
|---|
There are no public endpoints for this model yet.
An endpoint is a server with pre-installed software that automatically downloads neural network weights and launches an OpenAI-compatible API to handle incoming requests.
A private endpoint is created within the user's project, belongs exclusively to the user, and is billed per server configuration in accordance with the infrastructure pricing.
We recommend creating private endpoints when you need to:
| Name | GPU | TPS | Max Concurrency | |||
|---|---|---|---|---|---|---|
32,768.0 tensor |
2 | $0.93 | 8.336 | Launch | ||
32,768.0 pipeline |
3 | $1.06 | 5.842 | Launch | ||
32,768.0 tensor |
4 | $1.26 | 6.027 | Launch | ||
32,768.0 tensor |
2 | $1.56 | 57.97 | 9.359 | Launch | |
32,768.0 tensor |
2 | $1.56 | 9.359 | Launch | ||
32,768.0 |
1 | $1.59 | 3.122 | Launch | ||
32,768.0 tensor |
4 | $1.82 | 1.210 | Launch | ||
32,768.0 tensor |
2 | $1.92 | 68.06 | 9.320 | Launch | |
32,768.0 |
1 | $2.37 | 58.83 | 26.240 | Launch | |
32,768.0 |
1 | $3.83 | 54.91 | 26.206 | Launch | |
32,768.0 |
1 | $4.11 | 32.920 | Launch | ||
32,768.0 tensor |
2 | $4.61 | 63.113 | Launch | ||
32,768.0 |
1 | $4.74 | 55.463 | Launch | ||
32,768.0 tensor |
2 | $9.40 | 121.559 | Launch | ||
Contact our dedicated neural networks support team at support@immers.cloud or send your request to the sales department at sale@immers.cloud.