SurgeGlobal OpenBezoar HH RLHF 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 22 quants, from 2.0 GB (IQ3_S) to 3.6 GB (Q8_0).
3.43B llama model fine‑tuned on Anthropic HH‑RLHF
SurgeGlobal OpenBezoar HH RLHF SFT is a 3.43B parameter llama model. It was instruction fine‑tuned on 100K examples from the HH‑RLHF dataset. The model is released under a cc‑by‑nc‑4.0 license.
Good at
- Instruction following
- Text generation
- Language modeling
Limits
- No vision support
- Not aligned to human preferences
- May produce harmful content
Best for
- Chatbots with limited GPU
- Rapid prototyping
- Educational demos
Who it’s for. Developers and researchers who need a small llama model with instruction fine‑tuning. The model is suitable for non‑commercial use under the cc‑by‑nc‑4.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 2.0 GB | 3.2 GB | Fits | Get file → | |
| IQ3_XS | 2.0 GB | 3.2 GB | Fits | Get file → | |
| 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_NL | 2.0 GB | 3.2 GB | Fits | Get file → | |
| IQ4_XS | 2.0 GB | 3.2 GB | Fits | Get file → | |
| IQ3_M | 2.1 GB | 3.2 GB | Fits | Get file → | |
| Q3_K | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q4_1 | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q5_0 | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q4_K | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q5_1 | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q5_K | 2.8 GB | 3.9 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 → |
For 8 GB VRAM, use Q4_0 or Q4_1 (file size 1.98 GB or 2.19 GB, memory ~5.2 GB). For 12 GB VRAM, Q5_0 or Q5_1 (file size 2.4 GB or 2.6 GB, memory ~5.6 GB). Higher precision quants such as Q6_K or Q8_0 require ~6.9 GB memory and larger file sizes.
What GPU do you need for SurgeGlobal OpenBezoar HH RLHF 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 (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).
Which SurgeGlobal OpenBezoar HH RLHF SFT quant should you choose?
Q4_K_M is the usual starting point for SurgeGlobal OpenBezoar HH RLHF 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 IQ3_S at 2.0 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 SurgeGlobal OpenBezoar HH RLHF SFT
How much VRAM does SurgeGlobal OpenBezoar HH RLHF 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 SurgeGlobal OpenBezoar HH RLHF 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 SurgeGlobal OpenBezoar HH RLHF SFT GGUF?
It depends on the quant: IQ3_S is 2.0 GB, IQ3_XS is 2.0 GB, Q2_K is 2.0 GB, Q3_K_S is 2.0 GB, Q4_0 is 2.0 GB, IQ4_NL is 2.0 GB and 16 more.
What context length does SurgeGlobal OpenBezoar HH RLHF 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 SurgeGlobal OpenBezoar HH RLHF SFT GGUF?
The files are on Hugging Face in the RichardErkhov/SurgeGlobal_-_OpenBezoar-HH-RLHF-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 SurgeGlobal OpenBezoar HH RLHF 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 this model on 8 GB VRAM?
Yes, using Q4_0 or Q4_1 quantization will fit within 8 GB VRAM with an estimated 5.2 GB memory usage.
Is this model suitable for commercial deployment?
No, the cc‑by‑nc‑4.0 license restricts commercial use.
Does the model support image inputs?
No, the model has no vision capabilities.