KA

Karna 49M SFT Model

KarnaGGUF by VarunHujanUpdated 2026-10-18
Download on Hugging Face
Parameters72M
Context2K
Layers12
Architecturellama
Smallest quant0.0 GB
Quick answer

Karna 49M SFT Model needs about 0.7 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.0 GB (Q4_0) to 0.1 GB (F16).

Karna 49M SFT Model – a 49.38 M parameter SLM for narrative generation

Karna 49M SFT Model is a 49.38 M parameter small language model based on the llama architecture. It was trained from scratch and fine‑tuned with Supervised Fine‑Tuning using ChatML format. The model is licensed under MIT.

Good at

  • Long‑form narrative generation
  • Character‑anchored dialogues
  • Multi‑genre creative writing

Limits

  • No vision support
  • Context limited to 2048 tokens
  • No mixture of experts

Best for

  • Creative writing assistants
  • Story generation tools
  • Dialogue simulation

Who it’s for. Developers and writers looking for a lightweight model that can produce coherent stories and dialogues. The model is suitable for local deployment on modest hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.0 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.6 GB
Fits Get file →
F160.1 GB 0.7 GB
Fits Get file →

For 8 GB VRAM, the Q4_0 quantized file (0.04 GB) uses about 0.6 GB memory at 8 k context. Q8_0 (0.08 GB) uses about 0.7 GB. The F16 quant (0.15 GB) also uses about 0.7 GB. Choose the smallest quant for the lowest memory footprint.

What GPU do you need for Karna 49M SFT Model?

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 F16 (0.1 GB file, about 0.7 GB in use).

Which Karna 49M SFT Model quant should you choose?

Q8_0 (0.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters72M
Layers12
Trained context2,048 tokens
KV cache (fp16)11 KB per token

Source

Quantized byVarunHujan
FamilyKarna
Licensemit
Downloads (HF)28,987
Last updated2026-10-18

Frequently asked questions about Karna 49M SFT Model

How much VRAM does Karna 49M SFT Model need?

About 0.7 GB at Q8_0 with an 8K context window. That is the 0.1 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 Karna 49M SFT Model on an 8 GB GPU?

Yes, with F16: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Karna 49M SFT Model GGUF?

It depends on the quant: Q4_0 is 0.0 GB, Q8_0 is 0.1 GB, F16 is 0.1 GB.

What context length does Karna 49M SFT Model support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download Karna 49M SFT Model GGUF?

The files are on Hugging Face in the VarunHujan/Karna-49M-SFT-Model repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Karna 49M SFT Model use?

Hugging Face lists the license as mit. 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 Karna 49M on 8 GB VRAM?

Yes, the Q4_0 quantized model uses approximately 0.6 GB of VRAM at 8 k context, well within an 8 GB budget.

Does Karna 49M support image inputs?

No, the model has no vision capabilities.

What license does Karna 49M use?

The model is released under the MIT License.

Similar models

Browse all →

Other tiny models

All tiny models →