NuminaMath 72B TIR i1 needs about 50.6 GB of memory at Q4_K_M (a 47.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 22.7 GB (IQ1_S) to 47.4 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
72B‑parameter math LLM fine‑tuned with chain‑of‑thought and tool‑integrated reasoning
NuminaMath 72B TIR i1 is a 72.7B‑parameter model fine‑tuned on over 860k math problem‑solution pairs. It supports English and is optimized for complex mathematical reasoning and code generation. The model uses a 131072‑token context window.
Good at
- Math problem solving
- Chain‑of‑thought reasoning
- Python code generation
Limits
- Requires large VRAM (≈25–50 GB for lowest quants)
- No vision support
- License is other
Best for
- Academic research in math AI
- Developers building math‑centric assistants
- Educational tools for advanced problem solving
Who it’s for. Researchers, educators, and developers who need a high‑capacity model for mathematical reasoning and code generation. The model is suitable for environments with sufficient GPU memory and a need for extensive context handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 22.7 GB | 25.9 GB | Too big | Get file → | |
| IQ1_M | 23.7 GB | 26.9 GB | Too big | Get file → | |
| IQ2_XXS | 25.5 GB | 28.7 GB | Too big | Get file → | |
| IQ2_XS | 27.1 GB | 30.2 GB | Too big | Get file → | |
| IQ2_S | 27.9 GB | 31.1 GB | Too big | Get file → | |
| IQ2_M | 29.3 GB | 32.5 GB | Too big | Get file → | |
| Q2_K_S | 29.6 GB | 32.8 GB | Too big | Get file → | |
| Q2_K | 29.8 GB | 33.0 GB | Too big | Get file → | |
| IQ3_XXS | 31.8 GB | 35.0 GB | Too big | Get file → | |
| IQ3_XS | 32.8 GB | 36.0 GB | Too big | Get file → | |
| IQ3_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| Q3_K_S | 34.5 GB | 37.7 GB | Too big | Get file → | |
| IQ3_M | 35.5 GB | 38.7 GB | Too big | Get file → | |
| Q3_K_M | 37.7 GB | 40.9 GB | Too big | Get file → | |
| Q3_K_L | 39.5 GB | 42.7 GB | Too big | Get file → | |
| IQ4_XS | 39.7 GB | 42.9 GB | Too big | Get file → | |
| Q4_0 | 41.4 GB | 44.6 GB | Too big | Get file → | |
| Q4_K_S | 43.9 GB | 47.1 GB | Too big | Get file → | |
| Q4_K_M | 47.4 GB | 50.6 GB | Too big | Get file → |
For a 32 GB VRAM budget, IQ1_S (22.69 GB file, 25.9 GB memory at 8 k context) is a good choice. If 64 GB is available, IQ2_M (29.34 GB file, 32.5 GB memory) offers higher quality. For the lowest memory use, IQ1_S is recommended.
What GPU do you need for NuminaMath 72B TIR i1?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is IQ2_S (27.9 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_S (43.9 GB file, about 47.1 GB in use).
Which NuminaMath 72B TIR i1 quant should you choose?
Q4_K_M is the usual starting point for NuminaMath 72B TIR i1: it balances file size and quality well. Here it is a 47.4 GB file.
If memory is tight, the smallest file is IQ1_S at 22.7 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
Source
Frequently asked questions about NuminaMath 72B TIR i1
How much VRAM does NuminaMath 72B TIR i1 need?
About 50.6 GB at Q4_K_M with an 8K context window. That is the 47.4 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 72B TIR i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 25.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NuminaMath 72B TIR i1 GGUF?
It depends on the quant: IQ1_S is 22.7 GB, IQ1_M is 23.7 GB, IQ2_XXS is 25.5 GB, IQ2_XS is 27.1 GB, IQ2_S is 27.9 GB, IQ2_M is 29.3 GB and 13 more.
What context length does NuminaMath 72B TIR i1 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download NuminaMath 72B TIR i1 GGUF?
The files are on Hugging Face in the mradermacher/NuminaMath-72B-TIR-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 NuminaMath 72B TIR i1 use?
Hugging Face lists the license as other. 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 72B TIR i1 on 8 GB VRAM?
No, the smallest quant requires at least 25.9 GB of VRAM at 8 k context.
What is the maximum context length supported?
The model supports 131072 tokens of context.
Which quant has the lowest memory footprint?
IQ1_S has the lowest estimated memory usage of 25.9 GB at 8 k context.