NU

NuminaMath 7B TIR

NuminamathGGUF by QuantFactoryUpdated 2024-07-13
Download on Hugging Face
Parameters6.91B
Context4K
Layers30
Architecturellama
Smallest quant2.7 GB
Quick answer

NuminaMath 7B TIR 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 TIR – a 7B‑parameter math LLM fine‑tuned for tool‑integrated reasoning

NuminaMath 7B TIR is a 6.91B‑parameter language model specialized for solving mathematical problems. It is fine‑tuned in two stages: first on natural language math problem‑solution pairs, then on synthetic tool‑integrated reasoning data. The model is released under the Apache 2.0 license.

Good at

  • Math problem solving
  • Tool‑integrated reasoning with Python REPL
  • Chain‑of‑Thought explanations

Limits

  • No vision support
  • Requires 8K context for full functionality
  • Limited to English

Best for

  • Academic math tutoring
  • Competitive math problem solving
  • Automated math test generation

Who it’s for. Developers and educators who need a math‑focused LLM that can reason step‑by‑step and execute Python code. The model is ideal for building math tutoring tools or research projects involving mathematical reasoning.

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_K_M (4.22 GB file, ~8.7 GB memory). For 12 GB VRAM, Q5_K_M (4.93 GB file, ~9.5 GB memory) is suitable. For larger GPUs, Q6_K (5.67 GB file, ~10.2 GB memory) offers higher precision.

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: 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 TIR quant should you choose?

Q4_K_M is the usual starting point for NuminaMath 7B TIR: 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
Licenseapache-2.0
Downloads (HF)840
Last updated2024-07-13

Frequently asked questions about NuminaMath 7B TIR

How much VRAM does NuminaMath 7B TIR 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 TIR 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 TIR 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 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 QuantFactory/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 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 TIR on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires about 8.7 GB of VRAM at 8K context, which fits within an 8 GB GPU with some headroom.

Does the model support non‑English languages?

The model is primarily trained on English math problems and does not guarantee performance in other languages.

Is the model free to use?

Yes, it is released under the Apache 2.0 license, allowing free use and modification.

Other GGUFs of NuminaMath-7B-TIR

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Numinamath models

All Numinamath →

Other small models

All small models →