Amaretto 8B needs about 6.8 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Amaretto 8B – a fine‑tuned 8.49B‑parameter model for literary writing
Amaretto 8B is a 8.49B‑parameter language model built on Mistral‑3 architecture. It is fine‑tuned from Mistral‑3 8B Instruct using QLoRA for creative writing tasks. The model supports a 262144‑token context window and is released under the Apache‑2.0 license.
Good at
- Literary prose – scene writing, character voice
- Writing assistance – editing, tone adjustment
- Style transfer – formal ↔ casual, journalistic ↔ personal
Limits
- Fine‑tuned at 2048‑token sequences – long‑context quality not validated
- No vision support – only text
- Requires a system prompt for best literary output
Best for
- Creative writing assistants
- Editing and tone adjustment tools
- Style‑transfer applications
Who it’s for. Developers and writers who need a local, open‑source model for creative text generation. The model runs on everyday hardware and can be integrated via llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ1_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ2_XXS | 2.5 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XS | 2.7 GB | 4.4 GB | Fits | Get file → | |
| IQ2_S | 2.9 GB | 4.5 GB | Fits | Get file → | |
| IQ2_M | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_S | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q2_K | 3.4 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.5 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ3_S | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 4.2 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_L | 4.6 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 4.9 GB | 6.6 GB | Fits | Get file → | |
| IQ4_NL | 4.9 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_S | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_M | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_1 | 5.4 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_S | 5.9 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_M | 6.1 GB | 7.7 GB | Tight | Get file → | |
| Q6_K | 7.0 GB | 8.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.2 GB, estimated 6.8 GB memory at 8 k context). For 6 GB VRAM, Q3_K_M (4.24 GB, 5.9 GB memory) is a good choice. If only 4 GB VRAM is available, IQ2_XS (2.75 GB, 4.4 GB memory) provides the best trade‑off. Memory estimates are approximate.
What GPU do you need for Amaretto 8B?
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 IQ1_M (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.2 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 8.6 GB in use).
Which Amaretto 8B quant should you choose?
Q4_K_M is the usual starting point for Amaretto 8B: it balances file size and quality well. Here it is a 5.2 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 Amaretto 8B
How much VRAM does Amaretto 8B need?
About 6.8 GB at Q4_K_M with an 8K context window. That is the 5.2 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 Amaretto 8B on an 8 GB GPU?
Yes, with Q5_K_M: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Amaretto 8B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.
What context length does Amaretto 8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download Amaretto 8B GGUF?
The files are on Hugging Face in the mradermacher/Amaretto-8B-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 Amaretto 8B 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 Amaretto 8B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 6.8 GB of VRAM at 8 k context, leaving headroom for CPU memory and other processes.
Does Amaretto 8B support image inputs?
No, the model is text‑only; any mmproj files are not included in this release.
What license applies to Amaretto 8B?
The model is released under the Apache‑2.0 license, allowing commercial and non‑commercial use.