OR

Orbita v0.1

OrbitaGGUF by mradermacherUpdated 2024-12-04
Download on Hugging Face
Parameters14.2B
Context32K
Layers40
Architectureqwen2
Smallest quant4.5 GB
Quick answer

Orbita v0.1 needs about 16.4 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 4.5 GB (IQ1_S) to 12.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

Orbita v0.1 – a 14.2B Turkish LLM based on Qwen2

Orbita v0.1 is a Turkish Large Language Model with 14.2B parameters. It was fully finetuned on an annotated Turkish dataset using 8x H100 GPUs for two days. The model supports a wide range of Turkish language tasks such as coding and math.

Good at

  • Turkish instruction following
  • Coding in Turkish
  • Math problem solving

Limits

  • No vision support
  • Requires 8k context for full performance
  • Apache‑2.0 license

Best for

  • Local Turkish chatbot deployment
  • Educational coding assistant
  • Math tutoring in Turkish

Who it’s for. Developers and researchers needing a Turkish‑focused LLM for local inference. The model is available in GGUF format and can be run with llama.cpp on machines with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.5 GB 11.7 GB
Too big Get file →
IQ1_M4.7 GB 11.9 GB
Too big Get file →
IQ2_XXS5.0 GB 12.2 GB
Too big Get file →
IQ2_XS5.3 GB 12.5 GB
Too big Get file →
IQ2_S5.6 GB 12.8 GB
Too big Get file →
Q2_K_S5.7 GB 13.0 GB
Too big Get file →
IQ2_M5.8 GB 13.0 GB
Too big Get file →
Q2_K5.9 GB 13.1 GB
Too big Get file →
IQ3_XXS6.1 GB 13.3 GB
Too big Get file →
IQ3_XS6.5 GB 13.7 GB
Too big Get file →
IQ3_S6.8 GB 14.0 GB
Too big Get file →
Q3_K_S6.8 GB 14.0 GB
Too big Get file →
IQ3_M7.1 GB 14.3 GB
Too big Get file →
Q3_K_M7.4 GB 14.6 GB
Too big Get file →
Q3_K_L7.8 GB 15.1 GB
Too big Get file →
IQ4_XS7.8 GB 15.1 GB
Too big Get file →
Q4_08.2 GB 15.4 GB
Too big Get file →
Q4_08.2 GB 15.4 GB
Too big Get file →
Q4_08.2 GB 15.4 GB
Too big Get file →
Q4_08.2 GB 15.4 GB
Too big Get file →
Q4_K_S8.6 GB 15.8 GB
Too big Get file →
Q4_K_M9.2 GB 16.4 GB
Too big Get file →
Q5_K_S10.0 GB 17.2 GB
Too big Get file →
Q5_K_M10.5 GB 17.7 GB
Too big Get file →
Q6_K12.3 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.5 GB file, ~11.7 GB memory at 8k context). For 12 GB VRAM, IQ2_S (5.59 GB file, ~12.8 GB memory). For 16 GB VRAM, Q4_K_M (9.19 GB file, ~16.4 GB memory). Estimates are approximate.

What GPU do you need for Orbita v0.1?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ1_M (4.7 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (8.6 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 19.5 GB in use).

Which Orbita v0.1 quant should you choose?

Q4_K_M is the usual starting point for Orbita v0.1: it balances file size and quality well. Here it is a 9.2 GB file.

If memory is tight, the smallest file is IQ1_S at 4.5 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

Architectureqwen2
Parameters14.2B
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyOrbita
Licenseapache-2.0
Downloads (HF)1,649
Last updated2024-12-04

Frequently asked questions about Orbita v0.1

How much VRAM does Orbita v0.1 need?

About 16.4 GB at Q4_K_M with an 8K context window. That is the 9.2 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 Orbita v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Orbita v0.1 GGUF?

It depends on the quant: IQ1_S is 4.5 GB, IQ1_M is 4.7 GB, IQ2_XXS is 5.0 GB, IQ2_XS is 5.3 GB, IQ2_S is 5.6 GB, Q2_K_S is 5.7 GB and 19 more.

What context length does Orbita v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download Orbita v0.1 GGUF?

The files are on Hugging Face in the mradermacher/Orbita-v0.1-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 Orbita v0.1 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 Orbita v0.1 on 8 GB VRAM?

Yes, the IQ1_S quant requires about 11.7 GB memory at 8k context, which fits within 8 GB VRAM when using efficient batching.

Does Orbita v0.1 support vision tasks?

No, the model has no vision capabilities.

What license applies to Orbita v0.1?

The model is released under the Apache‑2.0 license.

Other GGUFs of Orbita-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Orbita models

All Orbita →

Other medium models

All medium models →