AgentCPM Explore needs about 4.4 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.2 GB (Q3_K_M) to 8.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
AgentCPM Explore – 4.41B‑parameter agent foundation model
AgentCPM Explore is a 4.41B‑parameter model built on the qwen3 architecture. It supports reasoning and tool use and is trained on 262144 context tokens. The model is released under the apache-2.0 license.
Good at
- Reasoning with tools
- Long‑horizon agent tasks
- Continuous environment interaction
Limits
- No vision support
- Requires at least 4 GB VRAM for Q3_K_M
- License is apache-2.0
Best for
- On‑device agent applications
- Long‑horizon task automation
- Tool‑enabled dialogue systems
Who it’s for. Developers building on‑device agents that need reasoning and tool use. Researchers testing long‑horizon benchmarks on modest hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 2.2 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.3 GB | Fits | Get file → | |
| F16 | 8.8 GB | 10.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_M (2.24 GB) or Q4_K_M (2.72 GB). If 12 GB VRAM is available, Q5_K_M (3.16 GB) or Q6_K (3.63 GB) provide higher precision. The F16 quant (8.83 GB) requires 10.5 GB VRAM at 8k context.
What GPU do you need for AgentCPM Explore?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q3_K_M (2.2 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.3 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.8 GB file, about 10.5 GB in use).
Which AgentCPM Explore quant should you choose?
Q4_K_M is the usual starting point for AgentCPM Explore: it balances file size and quality well. Here it is a 2.7 GB file.
If memory is tight, the smallest file is Q3_K_M at 2.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AgentCPM Explore
How much VRAM does AgentCPM Explore need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run AgentCPM Explore on an 8 GB GPU?
Yes, with Q6_K: the 3.6 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of AgentCPM Explore GGUF?
It depends on the quant: Q3_K_M is 2.2 GB, Q4_K_M is 2.7 GB, Q5_K_M is 3.2 GB, Q6_K is 3.6 GB, F16 is 8.8 GB.
What context length does AgentCPM Explore support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download AgentCPM Explore GGUF?
The files are on Hugging Face in the openbmb/AgentCPM-Explore-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does AgentCPM Explore use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run AgentCPM Explore on 8 GB VRAM?
Yes, the Q3_K_M quant is 2.24 GB and uses about 4 GB VRAM at 8k context. Q4_K_M is also suitable with 2.72 GB file size.
Does AgentCPM Explore support vision?
No, the model has no vision capability.
What license applies to AgentCPM Explore?
The model is released under the apache-2.0 license.