NU

NuminaMath-7B-TIR

NuminamathGGUF by ZeroWwUpdated 2024-07-12
Download on Hugging Face
Parameters6.91B
Context4K
Layers30
Architecturellama
Smallest quant6.0 GB
Quick answer

NuminaMath-7B-TIR needs about 11.9 GB of memory at its main file (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 6.0 GB (Q5_K) to 13.8 GB (F16).

NuminaMath-7B-TIR is a 6.91B-parameter Numinamath model in GGUF format, quantized by ZeroWw. Its trained context length is 4K tokens. The repository has 5 quant files, from 6.0 GB (Q5_K) to 13.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K6.0 GB 8.5 GB
Too big Get file →
Q6_K6.7 GB 9.2 GB
Too big Get file →
—7.3 GB 9.9 GB
Too big Get file →
Q8_08.1 GB 10.6 GB
Too big Get file →
F1613.8 GB 16.3 GB
Too big Get file →

What GPU do you need for NuminaMath-7B-TIR?

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 the main file (7.3 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 12.7 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.8 GB file, about 18.4 GB in use).

Which NuminaMath-7B-TIR quant should you choose?

If memory is tight, the smallest file is Q5_K at 6.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.91B
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized byZeroWw
Licensemit
Downloads (HF)87
Last updated2024-07-12

Frequently asked questions about NuminaMath-7B-TIR

How much VRAM does NuminaMath-7B-TIR need?

About 11.9 GB at its main file with an 8K context window. That is the 7.3 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 NuminaMath-7B-TIR on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NuminaMath-7B-TIR GGUF?

It depends on the quant: Q5_K is 6.0 GB, Q6_K is 6.7 GB, file is 7.3 GB, Q8_0 is 8.1 GB, F16 is 13.8 GB.

What context length does NuminaMath-7B-TIR support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

Where can I download NuminaMath-7B-TIR GGUF?

The files are on Hugging Face in the ZeroWw/NuminaMath-7B-TIR-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 NuminaMath-7B-TIR 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.

Similar models

Browse all →

More from ZeroWw

All by ZeroWw →

More Numinamath models

All Numinamath →

Other small models

All small models →