Selene 1 Llama 3.3 70B needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 23 quants, from 0.0 GB to 49.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Selene 1 Llama 3.3 70B – a large language model for evaluation tasks
Selene 1 is a 70.6 billion parameter model post‑trained from Llama‑3.3‑70B. It is designed for general‑purpose evaluation, supporting absolute scoring, classification, and pairwise preference tasks. The model has a 128K context length and primarily supports English with additional language support.
Good at
- Absolute scoring
- Classification
- Pairwise preference
Limits
- 128K context length
- No vision support
- Requires Llama 3.3 license
Best for
- Evaluating LLM responses
- RAG hallucination detection
- Agent performance assessment
Who it’s for. Researchers and developers needing a high‑quality evaluation model for language tasks. It is suitable for those who can provide the required prompt templates and have access to the Llama 3.3 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_S | 15.3 GB | 18.5 GB | Too big | Get file → | |
| IQ1_M | 16.8 GB | 19.9 GB | Too big | Get file → | |
| IQ2_XXS | 19.1 GB | 22.3 GB | Too big | Get file → | |
| IQ2_XS | 21.1 GB | 24.3 GB | Too big | Get file → | |
| IQ2_S | 22.2 GB | 25.4 GB | Too big | Get file → | |
| IQ2_M | 24.1 GB | 27.3 GB | Too big | Get file → | |
| Q2_K_S | 24.5 GB | 27.7 GB | Too big | Get file → | |
| Q2_K | 26.4 GB | 29.6 GB | Too big | Get file → | |
| IQ3_XXS | 27.5 GB | 30.7 GB | Too big | Get file → | |
| IQ3_XS | 29.3 GB | 32.5 GB | Too big | Get file → | |
| IQ3_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| Q3_K_S | 30.9 GB | 34.1 GB | Too big | Get file → | |
| IQ3_M | 31.9 GB | 35.1 GB | Too big | Get file → | |
| Q3_K_M | 34.3 GB | 37.5 GB | Too big | Get file → | |
| Q3_K_L | 37.1 GB | 40.3 GB | Too big | Get file → | |
| IQ4_XS | 37.9 GB | 41.1 GB | Too big | Get file → | |
| Q4_0 | 40.1 GB | 43.3 GB | Too big | Get file → | |
| Q4_K_S | 40.3 GB | 43.5 GB | Too big | Get file → | |
| Q4_K_M | 42.5 GB | 45.7 GB | Too big | Get file → | |
| Q4_1 | 44.3 GB | 47.5 GB | Too big | Get file → | |
| Q5_K_S | 48.7 GB | 51.8 GB | Too big | Get file → | |
| Q5_K_M | 49.9 GB | 53.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (40.12 GB file, 43.3 GB memory at 8K context). For 16 GB VRAM, Q3_K_M (34.27 GB file, 37.5 GB memory) or Q4_K_M (42.52 GB file, 45.7 GB memory). For 32 GB VRAM, Q5_K_M (49.95 GB file, 53.1 GB memory) offers higher quality. Estimates are approximate.
What GPU do you need for Selene 1 Llama 3.3 70B?
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 the main file (0.0 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_1 (44.3 GB file, about 47.5 GB in use).
Which Selene 1 Llama 3.3 70B quant should you choose?
Q4_K_M is the usual starting point for Selene 1 Llama 3.3 70B: it balances file size and quality well. Here it is a 42.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Selene 1 Llama 3.3 70B
How much VRAM does Selene 1 Llama 3.3 70B need?
About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Selene 1 Llama 3.3 70B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Selene 1 Llama 3.3 70B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB and 17 more.
What context length does Selene 1 Llama 3.3 70B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Selene 1 Llama 3.3 70B GGUF?
The files are on Hugging Face in the mradermacher/Selene-1-Llama-3.3-70B-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 Selene 1 Llama 3.3 70B use?
Hugging Face lists the license as llama3.3. 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 Selene 1 on 8 GB VRAM?
Use the Q4_0 quant; it requires about 43.3 GB memory at 8K context, which exceeds 8 GB VRAM, so it is not feasible.
Does Selene 1 support vision tasks?
No, the model has no vision support.
What license applies to Selene 1?
The model is licensed under llama3.3.