amalia-llm/AMALIA-9B-0626-SFT needs about 7.5 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.6 GB (Q4_K_M) to 9.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
AMALIA‑9B‑0626‑SFT: Open‑source Portuguese LLM
AMALIA‑9B‑0626‑SFT is a 9.15 billion‑parameter llama model fine‑tuned for European Portuguese. It supports a 32 768‑token context window and is released under Apache 2.0. The model is available in Q4_K_M and Q8_0 quantizations for llama.cpp.
Good at
- European Portuguese language tasks
- Instruction following
- Long‑context generation
Limits
- No vision support
- Requires 8 k context for memory estimates
- License is Apache 2.0
Best for
- Chatbots in Portuguese
- Content creation in European Portuguese
- Research on Portuguese NLP
Who it’s for. Developers and researchers needing a sovereign Portuguese language model. The model is suitable for applications that require instruction following and long‑context handling in European Portuguese.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.6 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 9.7 GB | 11.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.58 GB file, ~7.5 GB memory at 8 k context). For 12 GB VRAM, Q8_0 (9.73 GB file, ~11.6 GB memory at 8 k context) is recommended. Memory estimates are approximate.
What GPU do you need for amalia-llm/AMALIA-9B-0626-SFT?
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 Q4_K_M (5.6 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.7 GB file, about 11.6 GB in use).
Which amalia-llm/AMALIA-9B-0626-SFT quant should you choose?
Q4_K_M is the usual starting point for amalia-llm/AMALIA-9B-0626-SFT: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about amalia-llm/AMALIA-9B-0626-SFT
How much VRAM does amalia-llm/AMALIA-9B-0626-SFT need?
About 7.5 GB at Q4_K_M with an 8K context window. That is the 5.6 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 amalia-llm/AMALIA-9B-0626-SFT on an 8 GB GPU?
Yes, with Q4_K_M: the 5.6 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of amalia-llm/AMALIA-9B-0626-SFT GGUF?
It depends on the quant: Q4_K_M is 5.6 GB, Q8_0 is 9.7 GB.
What context length does amalia-llm/AMALIA-9B-0626-SFT support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download amalia-llm/AMALIA-9B-0626-SFT GGUF?
The files are on Hugging Face in the layerx-labs/AMALIA-9B-0626-SFT-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 amalia-llm/AMALIA-9B-0626-SFT 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 AMALIA‑9B‑0626‑SFT on 8 GB VRAM?
Yes, the Q4_K_M quantization uses about 7.5 GB of VRAM at 8 k context, fitting within an 8 GB GPU.
Does the model support vision tasks?
No, AMALIA‑9B‑0626‑SFT is a text‑only model.
What license applies to this model?
The model is released under the Apache 2.0 license.