HY

Hypernova 2x12B exp

HypernovaGGUF by mradermacherUpdated 2025-02-06
Download on Hugging Face
Parameters21.1B
Context128K
Layers40
Architecturellama
Smallest quant8.0 GB
Quick answer

Hypernova 2x12B exp needs about 14.7 GB of memory at Q4_K_M (a 12.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 8.0 GB (Q2_K) to 22.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Hypernova 2x12B exp is a 21.1B-parameter Hypernova model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 11 quant files, from 8.0 GB (Q2_K) to 22.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.0 GB 9.8 GB
Too big Get file →
Q3_K_S9.3 GB 11.2 GB
Too big Get file →
Q3_K_M10.3 GB 12.1 GB
Too big Get file →
Q3_K_L11.1 GB 12.9 GB
Too big Get file →
IQ4_XS11.5 GB 13.4 GB
Too big Get file →
Q4_K_S12.1 GB 14.0 GB
Too big Get file →
Q4_K_M12.8 GB 14.7 GB
Too big Get file →
Q5_K_S14.6 GB 16.4 GB
Too big Get file →
Q5_K_M15.0 GB 16.8 GB
Too big Get file →
Q6_K17.3 GB 19.1 GB
Too big Get file →
Q8_022.4 GB 24.2 GB
Too big Get file →

What GPU do you need for Hypernova 2x12B exp?

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 Q3_K_S (9.3 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (12.8 GB file, about 14.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (17.3 GB file, about 19.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.4 GB file, about 24.2 GB in use).

Which Hypernova 2x12B exp quant should you choose?

Q4_K_M is the usual starting point for Hypernova 2x12B exp: it balances file size and quality well. Here it is a 12.8 GB file.

The Q8_0 file is 22.4 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 Q2_K at 8.0 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
Parameters21.1B (approximate, mixture of experts)
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyHypernova
Downloads (HF)76
Last updated2025-02-06

Frequently asked questions about Hypernova 2x12B exp

How much VRAM does Hypernova 2x12B exp need?

About 14.7 GB at Q4_K_M with an 8K context window. That is the 12.8 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 Hypernova 2x12B exp on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Hypernova 2x12B exp GGUF?

It depends on the quant: Q2_K is 8.0 GB, Q3_K_S is 9.3 GB, Q3_K_M is 10.3 GB, Q3_K_L is 11.1 GB, IQ4_XS is 11.5 GB, Q4_K_S is 12.1 GB and 5 more.

What context length does Hypernova 2x12B exp support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Hypernova 2x12B exp GGUF?

The files are on Hugging Face in the mradermacher/Hypernova-2x12B-exp-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 Hypernova 2x12B exp use?

Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Hypernova-2x12B-exp

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Hypernova models

All Hypernova →

Other medium models

All medium models →