AH

Ahma 3B

AhmaGGUF by QuantFactoryUpdated 2025-07-02
Download on Hugging Face
Parameters3.63B
Context2K
Layers26
Architecturellama
Smallest quant2.1 GB
Quick answer

Ahma 3B needs about 6.0 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 14 quants, from 2.1 GB (Q2_K) to 3.9 GB (Q8_0).

Ahma 3B – 3.63B Finnish‑only Llama‑style decoder

Ahma 3B is a 3.63B parameter decoder‑only transformer based on Meta’s Llama (v1) architecture. It was pretrained from scratch on Finnish text and includes instruction‑following examples in its second training stage. The model is available in multiple GGUF quantizations.

Good at

  • Finnish text generation
  • Instruction following without fine‑tuning
  • Low‑resource inference

Limits

  • No multilingual or code generation
  • No vision support
  • License is apache‑2.0

Best for

  • Finnish chatbot prototypes
  • Fine‑tuning for Finnish NLP tasks
  • Local inference on modest GPUs

Who it’s for. Developers building Finnish‑language applications who need a lightweight, open‑source LLM. The model is suitable for researchers and hobbyists working with Finnish text and who prefer open‑source licensing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.1 GB 3.3 GB
Fits Get file →
Q3_K_S2.1 GB 3.3 GB
Fits Get file →
Q4_02.1 GB 3.3 GB
Fits Get file →
Q3_K_M2.3 GB 3.5 GB
Fits Get file →
Q4_12.4 GB 3.5 GB
Fits Get file →
Q3_K_L2.4 GB 3.6 GB
Fits Get file →
Q5_02.6 GB 3.8 GB
Fits Get file →
Q4_K_S2.6 GB 3.8 GB
Fits Get file →
Q4_K_M2.8 GB 3.9 GB
Fits Get file →
Q5_12.8 GB 4.0 GB
Fits Get file →
Q5_K_S2.8 GB 4.0 GB
Fits Get file →
Q5_K_M2.9 GB 4.1 GB
Fits Get file →
Q6_K3.9 GB 5.0 GB
Fits Get file →
Q8_03.9 GB 5.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 or Q4_1 (≈5.4–5.6 GB memory at 8 k context). For 12 GB VRAM, Q5_0 or Q5_1 (≈5.8–6.0 GB). For 16 GB VRAM, Q6_K or Q8_0 (≈7.1 GB). Estimates are approximate.

What GPU do you need for Ahma 3B?

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 Q5_1 (2.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (3.9 GB file, about 7.1 GB in use).

Which Ahma 3B quant should you choose?

Q4_K_M is the usual starting point for Ahma 3B: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 3.9 GB, about 1.4 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 2.1 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

Architecturellama
Parameters3.63B
Layers26
Trained context2,048 tokens
KV cache (fp16)325 KB per token

Source

Quantized byQuantFactory
FamilyAhma
Licenseapache-2.0
Downloads (HF)1,689
Last updated2025-07-02

Frequently asked questions about Ahma 3B

How much VRAM does Ahma 3B need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Ahma 3B on an 8 GB GPU?

Yes, with Q6_K: the 3.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ahma 3B GGUF?

It depends on the quant: Q2_K is 2.1 GB, Q3_K_S is 2.1 GB, Q4_0 is 2.1 GB, Q3_K_M is 2.3 GB, Q4_1 is 2.4 GB, Q3_K_L is 2.4 GB and 8 more.

What context length does Ahma 3B support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download Ahma 3B GGUF?

The files are on Hugging Face in the QuantFactory/Ahma-3B-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 Ahma 3B 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 Ahma 3B on 8 GB VRAM?

Yes, use a Q4 quantization such as Q4_0 or Q4_1, which requires about 5.4–5.6 GB of VRAM at 8 k context.

Does Ahma 3B support instruction following?

Yes, the model was trained with instruction examples and can follow prompts without additional fine‑tuning.

Is Ahma 3B multilingual?

No, it was trained only on Finnish text and is not suitable for multilingual or code generation tasks.

Other GGUFs of Ahma-3B

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Ahma models

All Ahma →

Other small models

All small models →