FaithEyes 7B SFT needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 3.8 GB (Q3_K_M) to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
FaithEyes 7B SFT – a vision‑language model with code‑based tool use and self‑judging.
FaithEyes 7B SFT is a supervised‑fine‑tuned VLM built on Qwen2.5‑VL‑7B‑Instruct. It supports coding, tools, and vision. The model is the cold‑start stage of the FaithEyes framework, providing code‑based tool use, faithfulness judging, and feedback‑driven reasoning.
Good at
- Code‑based tool use for image manipulation
- Self‑judging of process images
- Feedback‑driven reasoning
Limits
- No vision support beyond image inputs
- Large context length requires significant VRAM
- License is apache‑2.0
Best for
- Image‑based question answering with tool calls
- Automated image editing pipelines
- Research on multi‑agent VLMs
Who it’s for. Developers and researchers needing a VLM that can execute Python code for image manipulation and judge the usefulness of intermediate images. It is suitable for building agentic systems that require self‑feedback loops.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| BF16 | 15.2 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_M (file size 3.81 GB, estimated 4.8 GB memory). For 12 GB VRAM, Q4_K_M (4.68 GB, 5.7 GB memory) is a good balance. If more VRAM is available, BF16 (15.24 GB, 16.2 GB memory) offers the highest precision.
What GPU do you need for FaithEyes 7B SFT?
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 Q4_K_M (4.7 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.4 GB file, about 6.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (5.4 GB file, about 6.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (5.4 GB file, about 6.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).
Which FaithEyes 7B SFT quant should you choose?
Q4_K_M is the usual starting point for FaithEyes 7B SFT: it balances file size and quality well. Here it is a 4.7 GB file.
If memory is tight, the smallest file is Q3_K_M at 3.8 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 FaithEyes 7B SFT
How much VRAM does FaithEyes 7B SFT need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 FaithEyes 7B SFT on an 8 GB GPU?
Yes, with Q5_K_M: the 5.4 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FaithEyes 7B SFT GGUF?
It depends on the quant: Q3_K_M is 3.8 GB, Q3_K_L is 4.1 GB, Q4_K_S is 4.5 GB, Q4_K_M is 4.7 GB, Q5_K_S is 5.3 GB, Q5_K_M is 5.4 GB and 1 more.
What context length does FaithEyes 7B SFT support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download FaithEyes 7B SFT GGUF?
The files are on Hugging Face in the prithivMLmods/FaithEyes-7B-SFT-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 FaithEyes 7B SFT 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 FaithEyes 7B SFT on 8 GB VRAM?
Yes, the Q3_K_M quantized model requires approximately 4.8 GB memory at 8 k context, fitting within 8 GB VRAM.
Does this model support vision tasks?
Yes, it is a vision‑language model that can process images and perform image manipulation via code.
What license applies to this model?
The model is released under the apache‑2.0 license.