cpt7 needs about 4.9 GB of memory at Q6_K (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.8 GB (Q6_K) to 3.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
cpt7 – a 4.65B Gemma4 model with vision capability
cpt7 is a 4.65B parameter Gemma4 model fine‑tuned and converted to GGUF format. It supports vision tasks and can be run with llama.cpp or llama‑mtmd‑cli. The model is available in a Q6_K quantized GGUF file.
Good at
- Vision tasks
- Text generation
- Multimodal inference
Limits
- No license information provided
- Requires 4.9 GB VRAM at 8 k context
- No explicit language support listed
Best for
- Image captioning
- Visual question answering
- Multimodal chat
Who it’s for. Developers needing a lightweight vision‑enabled LLM for local deployment. Suitable for projects that can run GGUF models with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → |
The only available quant is Q6_K, 3.85 GB. It requires approximately 4.9 GB VRAM at 8 k context. For 8 GB VRAM users, Q6_K is suitable. No other quants are provided.
What GPU do you need for cpt7?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q6_K (3.8 GB file, about 4.9 GB in use).
Which cpt7 quant should you choose?
Q6_K (3.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about cpt7
How much VRAM does cpt7 need?
About 4.9 GB at Q6_K with an 8K context window. That is the 3.8 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 cpt7 on an 8 GB GPU?
Yes, with Q6_K: the 3.8 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of cpt7 GGUF?
It depends on the quant: Q6_K is 3.8 GB, Q6_K is 3.8 GB.
What context length does cpt7 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download cpt7 GGUF?
The files are on Hugging Face in the Agtian/cpt7 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run cpt7 on 8 GB VRAM?
Yes, the Q6_K quant requires about 4.9 GB VRAM at 8 k context, fitting within an 8 GB budget.
Does cpt7 support text only usage?
Yes, it can be used with llama-cli for text-only tasks.
What file size is the GGUF model?
The Q6_K GGUF file is 3.85 GB.