archangel_sft-kto_llama30b needs about 33.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 7.1 GB (IQ1_S) to 26.7 GB (Q6_K).
32‑billion‑parameter Llama model with SFT+KTO training and SHP alignment
archangel_sft-kto_llama30b is a 32‑billion‑parameter Llama model trained with SFT+KTO loss and aligned on SHP, Anthropic HH and Open Assistant data. It supports 2048‑token context and is released under Apache‑2.0.
Good at
- SFT+KTO fine‑tuning
- SHP and HH alignment
- Large context handling
Limits
- No vision support
- Requires 8‑k context for estimates
- Large VRAM needed for higher quants
Best for
- Research on aligned LLMs
- Fine‑tuning with custom datasets
- Benchmarking quantization effects
Who it’s for. Researchers and developers needing a large, aligned Llama model for experimentation. The model is open‑source and suitable for academic or non‑commercial use under Apache‑2.0.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 7.1 GB | 10.9 GB | Too big | Get file → | |
| IQ1_M | 7.7 GB | 11.5 GB | Too big | Get file → | |
| IQ2_XXS | 8.7 GB | 12.5 GB | Too big | Get file → | |
| IQ2_XS | 9.6 GB | 13.4 GB | Too big | Get file → | |
| IQ2_S | 10.4 GB | 14.2 GB | Too big | Get file → | |
| IQ2_M | 11.2 GB | 15.0 GB | Too big | Get file → | |
| Q2_K | 12.0 GB | 15.8 GB | Too big | Get file → | |
| IQ3_XXS | 12.3 GB | 16.1 GB | Too big | Get file → | |
| IQ3_XS | 13.3 GB | 17.1 GB | Too big | Get file → | |
| IQ3_S | 14.1 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_S | 14.1 GB | 17.8 GB | Too big | Get file → | |
| IQ3_M | 14.9 GB | 18.7 GB | Too big | Get file → | |
| Q3_K_M | 15.8 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 17.3 GB | 21.1 GB | Too big | Get file → | |
| IQ4_XS | 17.3 GB | 21.1 GB | Too big | Get file → | |
| Q4_0 | 18.4 GB | 22.2 GB | Too big | Get file → | |
| Q4_K_S | 18.5 GB | 22.3 GB | Too big | Get file → | |
| Q4_K_M | 19.6 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_S | 22.4 GB | 26.2 GB | Too big | Get file → | |
| Q5_K_M | 23.0 GB | 26.8 GB | Too big | Get file → | |
| Q6_K | 26.7 GB | 30.5 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (7.12 GB, ~20.7 GB RAM). For 12‑GB VRAM, IQ2_XS (9.64 GB, ~23.2 GB RAM). For 24‑GB VRAM, Q4_K_M (19.62 GB, ~33.2 GB RAM). Estimates are approximate.
What GPU do you need for archangel_sft-kto_llama30b?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ2_S (10.4 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_0 (18.4 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).
Which archangel_sft-kto_llama30b quant should you choose?
Q4_K_M is the usual starting point for archangel_sft-kto_llama30b: it balances file size and quality well. Here it is a 19.6 GB file.
If memory is tight, the smallest file is IQ1_S at 7.1 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 archangel_sft-kto_llama30b
How much VRAM does archangel_sft-kto_llama30b need?
About 33.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 archangel_sft-kto_llama30b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of archangel_sft-kto_llama30b GGUF?
It depends on the quant: IQ1_S is 7.1 GB, IQ1_M is 7.7 GB, IQ2_XXS is 8.7 GB, IQ2_XS is 9.6 GB, IQ2_S is 10.4 GB, IQ2_M is 11.2 GB and 15 more.
What context length does archangel_sft-kto_llama30b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.
Where can I download archangel_sft-kto_llama30b GGUF?
The files are on Hugging Face in the mradermacher/archangel_sft-kto_llama30b-i1-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 archangel_sft-kto_llama30b 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 archangel_sft-kto_llama30b on 8 GB VRAM?
Use the IQ1_S quant; it requires about 20.7 GB RAM at 8‑k context, which fits 8 GB VRAM with CPU fallback.
Does the model support image inputs?
No, the model has no vision capability.
What license applies to this model?
The model is released under the Apache‑2.0 license.