MI

colgrep-agent-2B

MiniCPMGGUF by lightonaiUpdated 2026-10-11
Download on Hugging Face
Parameters2.52B
Context128K
Layers42
Architecturellama
Smallest quant1.5 GB
Quick answer

colgrep-agent-2B needs about 2.4 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 1.5 GB (Q4_0) to 5.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.4 GB.

ColGrep-Agent-2B: lightweight code‑localization agent

ColGrep-Agent-2B is a 2.52B‑parameter model derived from MiniCPM5‑2B. It is designed to identify relevant files and line ranges in a repository for a given question. The model runs locally with GPU acceleration and requires no external inference server.

Good at

  • Code localization
  • Tool use
  • Long‑context search

Limits

  • No vision support
  • Requires 8k context for full performance
  • License is apache‑2.0

Best for

  • GitHub issue triage
  • Bug report analysis
  • Repository search

Who it’s for. Developers and teams needing quick, local code‑search assistance without large models. It is suitable for on‑device inference and resource‑constrained environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.5 GB 2.3 GB
Fits Get file →
Q4_K_M1.6 GB 2.4 GB
Fits Get file →
Q5_K_M1.8 GB 2.7 GB
Fits Get file →
Q6_K2.1 GB 2.9 GB
Fits Get file →
Q8_02.7 GB 3.5 GB
Fits Get file →
BF165.0 GB 5.9 GB
Fits Get file →
F165.0 GB 5.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 (file size 1.49 GB, ~2.3 GB memory at 8k context). If 12 GB VRAM is available, Q5_K_M (1.81 GB, ~2.7 GB memory) offers higher precision. Larger quants such as Q8_0 require more than 16 GB VRAM.

What GPU do you need for colgrep-agent-2B?

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 Q8_0 (2.7 GB file, about 3.5 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (5.0 GB file, about 5.9 GB in use).

Which colgrep-agent-2B quant should you choose?

Q4_K_M is the usual starting point for colgrep-agent-2B: it balances file size and quality well. Here it is a 1.6 GB file.

The Q8_0 file is 2.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 1.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters2.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)42 KB per token

Source

Quantized bylightonai
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)4,595
Last updated2026-10-11

Frequently asked questions about colgrep-agent-2B

How much VRAM does colgrep-agent-2B need?

About 2.4 GB at Q4_K_M with an 8K context window. That is the 1.6 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 colgrep-agent-2B on an 8 GB GPU?

Yes, with BF16: the 5.0 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of colgrep-agent-2B GGUF?

It depends on the quant: Q4_0 is 1.5 GB, Q4_K_M is 1.6 GB, Q5_K_M is 1.8 GB, Q6_K is 2.1 GB, Q8_0 is 2.7 GB, BF16 is 5.0 GB and 1 more.

What context length does colgrep-agent-2B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.4 GB at 32K.

Where can I download colgrep-agent-2B GGUF?

The files are on Hugging Face in the lightonai/colgrep-agent-2B-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 colgrep-agent-2B 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 ColGrep-Agent-2B on 8 GB VRAM?

Yes, the Q4_0 quant uses approximately 2.3 GB of VRAM at 8k context, which fits within an 8 GB GPU.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of MiniCPM5-2B

Similar models

Browse all →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →