LL

OpenMath2 Llama3.1 70B i1

LlamaGGUF by mradermacherUpdated 2024-10-11
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

OpenMath2 Llama3.1 70B i1 needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 20 quants, from 15.3 GB (IQ1_S) to 49.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

OpenMath2 Llama3.1 70B i1 – a math‑focused large language model

OpenMath2 Llama3.1 70B i1 is a 70.6B‑parameter model fine‑tuned on OpenMathInstruct‑2. It was trained with a context length of 131072 tokens and improves MATH scores by 3.9% over Llama3.1‑70B‑Instruct. The model is not instruction‑tuned for general use.

Good at

  • math problem solving
  • symbolic reasoning
  • numeric computation

Limits

  • not instruction‑tuned for general tasks
  • no vision support
  • requires large VRAM for full quant

Best for

  • solving math problems
  • generating math explanations
  • evaluating math datasets

Who it’s for. Researchers and developers who need a high‑quality math language model. The model excels in mathematical reasoning but is not suited for general conversational tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.3 GB 18.5 GB
Too big Get file →
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q4_040.1 GB 43.3 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →

For 8 GB VRAM, IQ1_S (15.34 GB file, ~18.5 GB memory at 8 k context) is the smallest option. If you have 12 GB VRAM, IQ1_M (16.75 GB file, ~19.9 GB memory) is suitable. For 16 GB VRAM, IQ2_XXS (19.1 GB file, ~22.3 GB memory) offers a balance between size and quality. Memory estimates are approximate.

What GPU do you need for OpenMath2 Llama3.1 70B 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: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which OpenMath2 Llama3.1 70B i1 quant should you choose?

Q4_K_M is the usual starting point for OpenMath2 Llama3.1 70B i1: it balances file size and quality well. Here it is a 42.5 GB file.

If memory is tight, the smallest file is IQ1_S at 15.3 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
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3.1
Downloads (HF)1,299
Last updated2024-10-11

Frequently asked questions about OpenMath2 Llama3.1 70B i1

How much VRAM does OpenMath2 Llama3.1 70B i1 need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 OpenMath2 Llama3.1 70B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OpenMath2 Llama3.1 70B i1 GGUF?

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB and 14 more.

What context length does OpenMath2 Llama3.1 70B 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 OpenMath2 Llama3.1 70B i1 GGUF?

The files are on Hugging Face in the mradermacher/OpenMath2-Llama3.1-70B-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 OpenMath2 Llama3.1 70B i1 use?

Hugging Face lists the license as llama3.1. 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 IQ1_S on 8 GB VRAM?

No. The model requires about 18.5 GB of VRAM at 8 k context, which exceeds 8 GB.

Does this model support vision?

No, it has no vision capabilities.

Is it instruction‑tuned for general tasks?

No, it is only fine‑tuned for the math domain.

Other GGUFs of OpenMath2-Llama3.1-70B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →