Fimbul-Airo-18B needs about 13.9 GB of memory at Q4_K_M (a 10.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 3.8 GB (IQ1_S) to 14.5 GB (Q6_K).
Fimbul-Airo-18B – 17.7B llama model in GGUF format
Fimbul-Airo-18B is a 17.7B parameter llama model merged from multiple sources. It supports a 4096 token context window and is available in a range of IQ and Q quantizations. The model is uncensored and uses Alpaca prompt format.
Good at
- Large context reasoning
- High token throughput
- Multi‑source knowledge
Limits
- No vision support
- License not specified
- Requires 8K context for full performance
Best for
- Chatbot development
- Text generation
- Research prototyping
Who it’s for. Developers and researchers who need a large llama model in GGUF format for local inference. The model is suitable for those who can manage the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.8 GB | 5.7 GB | Fits | Get file → | |
| IQ1_M | 4.2 GB | 6.0 GB | Fits | Get file → | |
| IQ2_XXS | 4.8 GB | 6.6 GB | Fits | Get file → | |
| IQ2_XS | 5.3 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 5.6 GB | 7.4 GB | Tight | Get file → | |
| IQ2_M | 6.0 GB | 7.9 GB | Tight | Get file → | |
| Q2_K | 6.6 GB | 8.5 GB | Too big | Get file → | |
| IQ3_XXS | 6.9 GB | 8.7 GB | Too big | Get file → | |
| IQ3_XS | 7.3 GB | 9.2 GB | Too big | Get file → | |
| IQ3_S | 7.8 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_S | 7.8 GB | 9.6 GB | Too big | Get file → | |
| IQ3_M | 8.0 GB | 9.8 GB | Too big | Get file → | |
| Q3_K_M | 8.6 GB | 10.4 GB | Too big | Get file → | |
| Q3_K_L | 9.3 GB | 11.2 GB | Too big | Get file → | |
| IQ4_XS | 9.5 GB | 11.3 GB | Too big | Get file → | |
| Q4_0 | 10.0 GB | 11.9 GB | Too big | Get file → | |
| Q4_K_S | 10.1 GB | 12.0 GB | Too big | Get file → | |
| Q4_K_M | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q5_K_S | 12.2 GB | 14.0 GB | Too big | Get file → | |
| Q5_K_M | 12.5 GB | 14.4 GB | Too big | Get file → | |
| Q6_K | 14.5 GB | 16.4 GB | Too big | Get file → |
For 8GB VRAM use IQ1_S (3.83 GB, 7 GB memory) or IQ1_M (4.19 GB, 7.4 GB). For 12GB VRAM use Q4_K_S (10.11 GB, 13.3 GB) or Q4_K_M (10.67 GB, 13.9 GB). For 16GB VRAM use Q5_K_S (12.2 GB, 15.4 GB) or Q5_K_M (12.53 GB, 15.7 GB).
What GPU do you need for Fimbul-Airo-18B?
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: the best quant that fits is IQ2_XXS (4.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_M (8.6 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (12.5 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (14.5 GB file, about 17.7 GB in use).
Which Fimbul-Airo-18B quant should you choose?
Q4_K_M is the usual starting point for Fimbul-Airo-18B: it balances file size and quality well. Here it is a 10.7 GB file.
If memory is tight, the smallest file is IQ1_S at 3.8 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 Fimbul-Airo-18B
How much VRAM does Fimbul-Airo-18B need?
About 13.9 GB at Q4_K_M with an 8K context window. That is the 10.7 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 Fimbul-Airo-18B on an 8 GB GPU?
Yes, with IQ2_XXS: the 4.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fimbul-Airo-18B GGUF?
It depends on the quant: IQ1_S is 3.8 GB, IQ1_M is 4.2 GB, IQ2_XXS is 4.8 GB, IQ2_XS is 5.3 GB, IQ2_S is 5.6 GB, IQ2_M is 6.0 GB and 15 more.
What context length does Fimbul-Airo-18B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download Fimbul-Airo-18B GGUF?
The files are on Hugging Face in the mradermacher/Fimbul-Airo-18B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Fimbul-Airo-18B on 8GB VRAM?
Use IQ1_S or IQ1_M quantizations; they require about 7–7.4 GB of VRAM at 8K context.
Does the model support vision?
No, the model has no vision capabilities.
What prompt format does it use?
It uses the Alpaca prompt format.