FaithEyes 8B SFT needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 7 quants, from 4.1 GB (Q3_K_M) to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
FaithEyes 8B SFT – a multi‑agent VLM with code‑based tool use and faithfulness judging
FaithEyes 8B SFT is a supervised‑fine‑tuned checkpoint of Qwen3‑VL‑8B‑Instruct. It equips the base model with code‑based tool use, faithfulness judging, and feedback‑driven reasoning. The model is released under the Apache‑2.0 license.
Good at
- Code‑based image manipulation
- Faithfulness judging of process images
- Feedback‑driven reasoning
Limits
- No reinforcement learning layer
- Requires 8 k context for memory estimates
- No vision support beyond image manipulation
Best for
- Building agents that use image tools
- Evaluating tool usefulness in visual QA
- Iterative reasoning with tool feedback
Who it’s for. Developers building vision‑language agents that need to generate and evaluate image‑based tool calls. Researchers exploring multi‑agent self‑judging frameworks may also find this checkpoint useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 4.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 4.4 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_S | 4.8 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.0 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.6 GB | Tight | Get file → | |
| BF16 | 16.4 GB | 18.1 GB | Too big | Get file → |
For 8 k context, Q4_K_M (5.03 GB file, 6.7 GB RAM) fits a 8 GB VRAM system. If VRAM is limited to 6 GB, Q3_K_M (4.12 GB file, 5.8 GB RAM) is a viable alternative. BF16 offers full precision but requires 18.1 GB RAM.
What GPU do you need for FaithEyes 8B 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 Q3_K_M (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).
Which FaithEyes 8B SFT quant should you choose?
Q4_K_M is the usual starting point for FaithEyes 8B SFT: it balances file size and quality well. Here it is a 5.0 GB file.
If memory is tight, the smallest file is Q3_K_M at 4.1 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 8B SFT
How much VRAM does FaithEyes 8B SFT need?
About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 8B SFT on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FaithEyes 8B SFT GGUF?
It depends on the quant: Q3_K_M is 4.1 GB, Q3_K_L is 4.4 GB, Q4_K_S is 4.8 GB, Q4_K_M is 5.0 GB, Q5_K_S is 5.7 GB, Q5_K_M is 5.9 GB and 1 more.
What context length does FaithEyes 8B SFT 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 FaithEyes 8B SFT GGUF?
The files are on Hugging Face in the prithivMLmods/FaithEyes-8B-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 8B 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 8B SFT on 8 GB VRAM?
Yes, using Q4_K_M or Q3_K_M quantizations will fit within 8 GB VRAM with 8 k context.
Does this model support image generation?
No, it only supports image manipulation tools and does not generate images.
Is reinforcement learning included?
No, this is the SFT cold‑start checkpoint; RL is added in a separate FaithEyes‑8B‑RL model.