DE

NuminaMath 7B CoT

DeepSeekGGUF by QuantFactoryUpdated 2024-07-22
Download on Hugging Face
Parameters6.91B
Context4K
Layers30
Architecturellama
Smallest quant2.7 GB
Quick answer

NuminaMath 7B CoT needs about 8.7 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 2.7 GB (Q2_K) to 7.3 GB (Q8_0).

NuminaMath 7B CoT – a math‑focused LLM

NuminaMath 7B CoT is a 6.91 billion‑parameter model fine‑tuned on 860k+ math competition problem‑solution pairs. It is built on deepseek‑math‑7b‑base and uses chain‑of‑thought reasoning. The model is licensed under Apache‑2.0 and supports commercial use.

Good at

  • Solving competition‑level math problems
  • Chain‑of‑thought reasoning
  • Tool‑integrated reasoning

Limits

  • No vision support
  • Not suited for general chat
  • Requires 8 k context for full performance

Best for

  • Math tutoring
  • Competitive exam prep
  • Automated math problem solving

Who it’s for. Developers and researchers needing a specialized math LLM. The model is ideal for educational tools and math competition preparation, but not for general conversational applications.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 5.2 GB
Fits Get file →
Q3_K_S3.1 GB 5.7 GB
Fits Get file →
Q3_K_M3.5 GB 6.0 GB
Fits Get file →
Q3_K_L3.7 GB 6.3 GB
Fits Get file →
Q4_04.0 GB 6.5 GB
Fits Get file →
Q4_K_S4.0 GB 6.5 GB
Fits Get file →
Q4_K_M4.2 GB 6.7 GB
Fits Get file →
Q4_14.4 GB 6.9 GB
Fits Get file →
Q5_04.8 GB 7.3 GB
Tight Get file →
Q5_K_S4.8 GB 7.3 GB
Tight Get file →
Q5_K_M4.9 GB 7.4 GB
Tight Get file →
Q5_15.2 GB 7.7 GB
Tight Get file →
Q6_K5.7 GB 8.2 GB
Too big Get file →
Q8_07.3 GB 9.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (4 GB file, 8.5 GB memory) or Q4_K_S (4.03 GB file, 8.6 GB memory). For 12 GB VRAM, Q5_1 (5.22 GB file, 9.7 GB memory) or Q6_K (5.67 GB file, 10.2 GB memory) are suitable. Larger VRAM allows Q8_0 (7.35 GB file, 11.9 GB memory).

What GPU do you need for NuminaMath 7B CoT?

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: the best quant that fits is Q3_K_M (3.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 11.9 GB in use).

Which NuminaMath 7B CoT quant should you choose?

Q4_K_M is the usual starting point for NuminaMath 7B CoT: it balances file size and quality well. Here it is a 4.2 GB file.

The Q8_0 file is 7.3 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 2.7 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
Parameters6.91B
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized byQuantFactory
FamilyDeepSeek
Licenseapache-2.0
Downloads (HF)949
Last updated2024-07-22

Frequently asked questions about NuminaMath 7B CoT

How much VRAM does NuminaMath 7B CoT need?

About 8.7 GB at Q4_K_M with an 8K context window. That is the 4.2 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 CoT on an 8 GB GPU?

Yes, with Q3_K_M: the 3.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NuminaMath 7B CoT GGUF?

It depends on the quant: Q2_K is 2.7 GB, Q3_K_S is 3.1 GB, Q3_K_M is 3.5 GB, Q3_K_L is 3.7 GB, Q4_0 is 4.0 GB, Q4_K_S is 4.0 GB and 8 more.

What context length does NuminaMath 7B CoT 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 CoT GGUF?

The files are on Hugging Face in the QuantFactory/NuminaMath-7B-CoT-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 CoT 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.

Can I run NuminaMath 7B CoT on 8 GB VRAM?

Yes, use the Q4_0 or Q4_K_S quantized models; they require about 8.5–8.6 GB VRAM at 8 k context.

Does the model support vision inputs?

No, NuminaMath 7B CoT is a text‑only model and has no vision capability.

What license applies to the model?

The model is released under the Apache‑2.0 license, allowing commercial use.

Other GGUFs of deepseek-math-7b-base

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More DeepSeek models

All DeepSeek →

Other small models

All small models →