Hypernova 60B 2602 needs about 41.7 GB of memory at Q4_K_M (a 40.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 24 quants, from 0.1 GB to 57.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Hypernova 60B 2602 is a 58.7B-parameter Hypernova model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 24 quant files, from 0.1 GB to 57.8 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.1 GB | Fits | Get file → | |
| IQ1_S | 26.7 GB | 27.7 GB | Too big | Get file → | |
| IQ1_M | 27.1 GB | 28.1 GB | Too big | Get file → | |
| IQ2_XXS | 27.7 GB | 28.7 GB | Too big | Get file → | |
| IQ2_XS | 28.2 GB | 29.3 GB | Too big | Get file → | |
| IQ2_S | 28.5 GB | 29.6 GB | Too big | Get file → | |
| IQ2_M | 29.0 GB | 30.1 GB | Too big | Get file → | |
| Q2_K_S | 29.4 GB | 30.5 GB | Too big | Get file → | |
| IQ3_XXS | 30.0 GB | 31.0 GB | Too big | Get file → | |
| Q3_K_S | 30.8 GB | 31.9 GB | Too big | Get file → | |
| IQ3_S | 30.8 GB | 31.9 GB | Too big | Get file → | |
| IQ3_XS | 30.8 GB | 31.9 GB | Too big | Get file → | |
| Q2_K | 30.8 GB | 31.9 GB | Too big | Get file → | |
| IQ3_M | 31.2 GB | 32.2 GB | Too big | Get file → | |
| IQ4_XS | 32.8 GB | 33.8 GB | Too big | Get file → | |
| Q4_0 | 33.5 GB | 34.6 GB | Too big | Get file → | |
| Q3_K_M | 33.5 GB | 34.6 GB | Too big | Get file → | |
| Q3_K_L | 35.8 GB | 36.8 GB | Too big | Get file → | |
| Q4_1 | 37.0 GB | 38.1 GB | Too big | Get file → | |
| Q4_K_S | 38.5 GB | 39.6 GB | Too big | Get file → | |
| Q4_K_M | 40.7 GB | 41.7 GB | Too big | Get file → | |
| Q5_K_S | 43.1 GB | 44.1 GB | Too big | Get file → | |
| Q5_K_M | 44.3 GB | 45.4 GB | Too big | Get file → | |
| Q6_K | 57.8 GB | 58.8 GB | Too big | Get file → |
What GPU do you need for Hypernova 60B 2602?
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 the main file (0.1 GB file, about 1.1 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.1 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.1 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.1 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.1 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_S (30.8 GB file, about 31.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q5_K_M (44.3 GB file, about 45.4 GB in use).
Which Hypernova 60B 2602 quant should you choose?
Q4_K_M is the usual starting point for Hypernova 60B 2602: it balances file size and quality well. Here it is a 40.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Hypernova 60B 2602
How much VRAM does Hypernova 60B 2602 need?
About 41.7 GB at Q4_K_M with an 8K context window. That is the 40.7 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 60B 2602 on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hypernova 60B 2602 GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 26.7 GB, IQ1_M is 27.1 GB, IQ2_XXS is 27.7 GB, IQ2_XS is 28.2 GB, IQ2_S is 28.5 GB and 18 more.
What context length does Hypernova 60B 2602 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download Hypernova 60B 2602 GGUF?
The files are on Hugging Face in the mradermacher/Hypernova-60B-2602-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 Hypernova 60B 2602 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.