STAIR Llama 3.1 8B SFT i1 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
STAIR Llama 3.1 8B SFT i1 – fine‑tuned Llama 3.1 for step‑by‑step reasoning
STAIR Llama 3.1 8B SFT i1 is a fine‑tuned version of meta‑llama/Llama‑3.1‑8B‑Instruct on the STAIR‑SFT dataset. It outputs reasoning steps followed by a final answer. The model supports tool usage and is released under the apache‑2.0 license.
Good at
- Tool‑enabled reasoning
- Step‑by‑step answer generation
- Fine‑tuned for safety and correctness
Limits
- No vision support
- Requires 8k context for memory estimates
- Large VRAM needed for higher quants
Best for
- Developers building reasoning assistants
- Researchers testing step‑wise LLM outputs
- Applications needing tool integration
Who it’s for. This model is suited for developers and researchers who need a fine‑tuned Llama 3.1 capable of generating step‑by‑step reasoning and using tools. It is ideal for building assistants that require clear reasoning traces and safe outputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.0 GB | 3.6 GB | Fits | Get file → | |
| IQ1_M | 2.2 GB | 3.7 GB | Fits | Get file → | |
| IQ2_XXS | 2.4 GB | 4.0 GB | Fits | Get file → | |
| IQ2_XS | 2.6 GB | 4.2 GB | Fits | Get file → | |
| IQ2_S | 2.8 GB | 4.3 GB | Fits | Get file → | |
| IQ2_M | 2.9 GB | 4.5 GB | Fits | Get file → | |
| Q2_K_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q2_K | 3.2 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XXS | 3.3 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XS | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_S | 3.7 GB | 5.2 GB | Fits | Get file → | |
| IQ3_S | 3.7 GB | 5.3 GB | Fits | Get file → | |
| IQ3_M | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 4.4 GB | 6.0 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 6.3 GB | Fits | Get file → | |
| IQ4_NL | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_1 | 5.1 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.6 GB | 8.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.02 GB, 3.6 GB memory at 8k context) or IQ1_M (2.16 GB, 3.7 GB memory). If you have 12 GB VRAM, Q4_K_M (4.92 GB, 6.5 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (5.73 GB, 7.3 GB memory) offers higher quality.
What GPU do you need for STAIR Llama 3.1 8B SFT i1?
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: the best quant that fits is IQ2_XXS (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).
Which STAIR Llama 3.1 8B SFT i1 quant should you choose?
Q4_K_M is the usual starting point for STAIR Llama 3.1 8B SFT i1: it balances file size and quality well. Here it is a 4.9 GB file.
If memory is tight, the smallest file is IQ1_S 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 STAIR Llama 3.1 8B SFT i1
How much VRAM does STAIR Llama 3.1 8B SFT i1 need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 STAIR Llama 3.1 8B SFT i1 on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of STAIR Llama 3.1 8B SFT i1 GGUF?
It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 18 more.
What context length does STAIR Llama 3.1 8B SFT i1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download STAIR Llama 3.1 8B SFT i1 GGUF?
The files are on Hugging Face in the mradermacher/STAIR-Llama-3.1-8B-SFT-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 STAIR Llama 3.1 8B SFT i1 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 this model on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations; they require about 3.6–3.7 GB memory at 8k context.
Does this model support vision?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.