SU

SuperNova Medius

SupernovaGGUF by duyntnetUpdated 2024-11-24
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant3.6 GB
Quick answer

SuperNova Medius needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 27 quants, from 3.6 GB (IQ1_S) to 15.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

14B Qwen2-based model optimized for instruction following

SuperNova Medius is a 14.8B parameter language model built on the Qwen2 architecture. It supports tool usage and is designed for business applications such as customer support, content creation, and technical assistance. The model is available in multiple GGUF quantizations for various hardware budgets.

Good at

  • Instruction following
  • Tool integration
  • Business content generation

Limits

  • No vision support
  • License type: other
  • Context length limited to 131072 tokens

Best for

  • Customer support bots
  • Content creation pipelines
  • Technical assistance tools

Who it’s for. Developers and organizations needing a mid-sized, instruction‑oriented model that can run on modest hardware. The model is suitable for teams that require tool‑enabled reasoning without the need for vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.6 GB 5.7 GB
Fits Get file →
IQ1_M3.9 GB 6.0 GB
Fits Get file →
IQ2_XXS4.3 GB 6.4 GB
Fits Get file →
IQ2_XS4.7 GB 6.8 GB
Fits Get file →
IQ2_S5.0 GB 7.1 GB
Fits Get file →
IQ2_M5.4 GB 7.5 GB
Tight Get file →
Q2_K_S5.4 GB 7.5 GB
Tight Get file →
Q2_K5.8 GB 7.9 GB
Tight Get file →
IQ3_XXS5.9 GB 8.1 GB
Too big Get file →
IQ3_XS6.4 GB 8.5 GB
Too big Get file →
Q3_K_S6.7 GB 8.8 GB
Too big Get file →
IQ3_S6.7 GB 8.8 GB
Too big Get file →
IQ3_M6.9 GB 9.0 GB
Too big Get file →
Q3_K_M7.3 GB 9.4 GB
Too big Get file →
Q3_K_L7.9 GB 10.0 GB
Too big Get file →
IQ4_XS8.1 GB 10.2 GB
Too big Get file →
Q4_08.5 GB 10.7 GB
Too big Get file →
IQ4_NL8.5 GB 10.7 GB
Too big Get file →
Q4_K_S8.6 GB 10.7 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 GB
Too big Get file →
Q4_19.4 GB 11.5 GB
Too big Get file →
Q5_K_S10.3 GB 12.4 GB
Too big Get file →
Q5_010.3 GB 12.4 GB
Too big Get file →
Q5_K_M10.5 GB 12.6 GB
Too big Get file →
Q5_111.1 GB 13.3 GB
Too big Get file →
Q6_K12.1 GB 14.2 GB
Too big Get file →
Q8_015.7 GB 17.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.61 GB, estimated memory 5.7 GB at 8 k context). For 12 GB VRAM, Q4_K_M (8.99 GB, 11.1 GB memory) or Q5_K_M (10.51 GB, 12.6 GB memory) are suitable. Larger GPUs can handle Q6_K or Q8_0 for higher precision.

What GPU do you need for SuperNova Medius?

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 IQ1_M (3.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q2_K (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (9.4 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.7 GB file, about 17.8 GB in use).

Which SuperNova Medius quant should you choose?

Q4_K_M is the usual starting point for SuperNova Medius: it balances file size and quality well. Here it is a 9.0 GB file.

The Q8_0 file is 15.7 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.

If memory is tight, the smallest file is IQ1_S at 3.6 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
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized byduyntnet
FamilySupernova
Licenseother
Downloads (HF)566
Last updated2024-11-24

Frequently asked questions about SuperNova Medius

How much VRAM does SuperNova Medius need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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 SuperNova Medius on an 8 GB GPU?

Yes, with Q2_K: the 5.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SuperNova Medius GGUF?

It depends on the quant: IQ1_S is 3.6 GB, IQ1_M is 3.9 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 5.0 GB, IQ2_M is 5.4 GB and 21 more.

What context length does SuperNova Medius support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download SuperNova Medius GGUF?

The files are on Hugging Face in the duyntnet/SuperNova-Medius-imatrix-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 SuperNova Medius use?

Hugging Face lists the license as other. 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 SuperNova Medius on 8 GB VRAM?

Yes, the IQ1_S quantization requires about 5.7 GB of VRAM at 8 k context, fitting within an 8 GB budget.

Does the model support image inputs?

No, SuperNova Medius does not include vision capabilities.

What inference clients are compatible?

Supported clients include llama.cpp, KoboldCPP, ollama, text-generation-webui, GPT4All, and jan.

Similar models

Browse all →

More from duyntnet

All by duyntnet →

More Supernova models

All Supernova →

Other medium models

All medium models →