NU

NuminaMath 7B TIR

NuminamathGGUF by kawchar85Updated 2024-10-12
Download on Hugging Face
Parameters6.91B
Context4K
Layers30
Architecturellama
Smallest quant5.7 GB
Quick answer

NuminaMath 7B TIR needs about 10.2 GB of memory at Q6_K (a 5.7 GB file) with an 8K context window, so it fits on a 12 GB GPU.

NuminaMath 7B TIR is a 6.91B-parameter Numinamath model in GGUF format, quantized by kawchar85. Its trained context length is 4K tokens. The repository has 1 quant file, from 5.7 GB (Q6_K) to 5.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K5.7 GB 8.2 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 Q6_K (5.7 GB file, about 10.2 GB in use).

Which NuminaMath 7B TIR quant should you choose?

Q6_K (5.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

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 bykawchar85
Licenseapache-2.0
Downloads (HF)16
Last updated2024-10-12

Frequently asked questions about NuminaMath 7B TIR

How much VRAM does NuminaMath 7B TIR need?

About 10.2 GB at Q6_K with an 8K context window. That is the 5.7 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 NuminaMath 7B TIR on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.2 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: Q6_K is 5.7 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 kawchar85/NuminaMath-7B-TIR-Q6_K-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 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.

Other GGUFs of NuminaMath-7B-TIR

Similar models

Browse all →

More from kawchar85

All by kawchar85 →

More Numinamath models

All Numinamath →

Other small models

All small models →