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 12 quants, from 3.4 GB (Q2_K) to 17.0 GB (F16). 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 model built on Mistral3. It is fine‑tuned for literary prose, editing, and style transfer. The model supports tools and vision and can run on everyday hardware.
Good at
- Literary prose and scene writing
- Writing assistance and tone adjustment
- Style transfer between registers
Limits
- No vision support in GGUF quantized versions
- Context window 262144 tokens but long‑context quality not validated
- Requires 8k context for memory estimates
Best for
- Creative writing assistants
- Editing and tone refinement
- Style transfer tasks
Who it’s for. Developers and writers who need a local, open‑source model for creative writing. The model is suitable for edge deployment and can be used with llama.cpp or Ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.4 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.5 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 | 6.4 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 → | |
| 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 → | |
| Q8_0 | 9.0 GB | 10.7 GB | Too big | Get file → | |
| F16 | 17.0 GB | 18.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.2 GB file, 6.8 GB memory at 8k context). For 12 GB VRAM, use Q5_K_M (6.06 GB file, 7.7 GB memory). For 16 GB VRAM, use Q6_K (6.97 GB file, 8.6 GB memory).
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: no quant fits at an 8K context.
- 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 Q8_0 (9.0 GB file, about 10.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 10.7 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.0 GB file, about 18.6 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.
The Q8_0 file is 9.0 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.4 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 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: Q2_K is 3.4 GB, Q3_K_S is 3.9 GB, Q3_K_M is 4.2 GB, Q3_K_L is 4.6 GB, IQ4_XS is 4.7 GB, Q4_K_S is 5.0 GB and 6 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-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, using the Q4_K_M quantized file (5.2 GB) will fit within 8 GB VRAM with an estimated 6.8 GB memory usage at 8k context.
Does the model support vision?
The detected abilities include vision, but the GGUF quantized files do not provide vision support.
What context length can I use?
The model has a trained context of 262144 tokens; you can raise the context size with --ctx-size, but long‑context quality has not been specifically validated.