OpenBezoar SFT needs about 5.8 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 13 quants, from 2.0 GB (Q2_K) to 6.9 GB (F16).
OpenBezoar SFT – 3.43B instruction‑tuned LLaMA model
OpenBezoar SFT is a 3.43B parameter LLaMA model fine‑tuned with Q‑LoRA on custom instruction datasets. It is released under a cc‑by‑nc‑4.0 license and supports a 2048 token context window.
Good at
- Instruction following
- Custom prompt templates
- Non‑vision tasks
Limits
- No vision support
- Not aligned to human preferences
- May generate harmful content
Best for
- Chatbots with limited VRAM
- Rapid prototyping of instruction‑based agents
- Educational demos
Who it’s for. Developers and researchers who need a lightweight instruction‑tuned LLaMA model for experimentation. The model is suitable for non‑commercial use only due to its license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_S | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_0 | 2.0 GB | 3.2 GB | Fits | Get file → | |
| IQ4_XS | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 3.9 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 3.6 GB | 4.8 GB | Fits | Get file → | |
| F16 | 6.9 GB | 8.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (2.58 GB file, ~5.8 GB memory) or Q5_K_M (2.76 GB file, ~6 GB memory). If memory is tighter, Q4_0 (1.98 GB file, ~5.2 GB memory) is a good trade‑off. Higher‑quality quants like F16 require ~10.1 GB memory and are unsuitable for 8 GB VRAM.
What GPU do you need for OpenBezoar 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 Q5_K_M (2.8 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.9 GB file, about 10.1 GB in use).
Which OpenBezoar SFT quant should you choose?
Q4_K_M is the usual starting point for OpenBezoar SFT: it balances file size and quality well. Here it is a 2.6 GB file.
The Q8_0 file is 3.6 GB, about 1.4 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 Q2_K at 2.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OpenBezoar SFT
How much VRAM does OpenBezoar SFT need?
About 5.8 GB at Q4_K_M with an 8K context window. That is the 2.6 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 OpenBezoar SFT on an 8 GB GPU?
Yes, with Q6_K: the 3.6 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of OpenBezoar SFT GGUF?
It depends on the quant: Q2_K is 2.0 GB, Q3_K_S is 2.0 GB, Q4_0 is 2.0 GB, IQ4_XS is 2.0 GB, Q3_K_M is 2.1 GB, Q3_K_L is 2.2 GB and 7 more.
What context length does OpenBezoar SFT support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.
Where can I download OpenBezoar SFT GGUF?
The files are on Hugging Face in the mradermacher/OpenBezoar-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 OpenBezoar SFT use?
Hugging Face lists the license as cc-by-nc-4.0. 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 OpenBezoar SFT on 8 GB VRAM?
Yes, use the Q4_K_M or Q5_K_M quant, which estimate 5.8–6 GB memory at 8k context.
Does this model support image inputs?
No, the model has no vision capability.
Is this model suitable for production use?
The model is not aligned to human preferences and may generate harmful content; it is not recommended for production.