WI

wizardlm_wizardmath-70b-v1.0

WizardmathGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters69B
Context2K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

wizardlm_wizardmath-70b-v1.0 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M).

WizardMath 70B V1.0 – a large‑scale math‑focused LLM in GGUF format

WizardMath 70B V1.0 is a 69‑billion‑parameter model trained for mathematical reasoning. It is available in multiple GGUF quantisations and supports a 2048‑token context window. The model is released under the llama2 license.

Good at

  • Mathematical problem solving
  • Reasoning with step‑by‑step explanations
  • High‑accuracy numeric calculations

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is llama2

Best for

  • Solving algebraic equations
  • Generating math proofs
  • Assisting in STEM education

Who it’s for. Researchers and developers needing a large, math‑specialised LLM for local inference. The model is suitable for users with GPU resources capable of handling 70B parameters in a quantised form.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.3 GB 30.5 GB
Too big Get file →
Q3_K_S29.9 GB 31.1 GB
Too big Get file →
Q3_K_M33.2 GB 34.4 GB
Too big Get file →
Q3_K_L36.1 GB 37.3 GB
Too big Get file →
Q4_038.9 GB 40.0 GB
Too big Get file →
Q4_K_S39.1 GB 40.2 GB
Too big Get file →
Q4_K_M41.4 GB 42.6 GB
Too big Get file →
Q5_047.5 GB 48.6 GB
Too big Get file →
Q5_K_S47.5 GB 48.6 GB
Too big Get file →
Q5_K_M48.8 GB 49.9 GB
Too big Get file →

For 8‑GB VRAM use Q4_K (file size 38.87 GB, ~42.1 GB memory at 8k context). For 16‑GB VRAM use Q5_K_M (file size 48.75 GB, ~51.9 GB memory). Higher quants such as Q3_K_L or Q4_K_M provide better quality but need more memory.

What GPU do you need for wizardlm_wizardmath-70b-v1.0?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which wizardlm_wizardmath-70b-v1.0 quant should you choose?

Q4_K_M is the usual starting point for wizardlm_wizardmath-70b-v1.0: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.3 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
Parameters69B
Layers80
Trained context2,048 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
Licensellama2
Downloads (HF)1,418
Last updated2023-09-27

Frequently asked questions about wizardlm_wizardmath-70b-v1.0

How much VRAM does wizardlm_wizardmath-70b-v1.0 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 wizardlm_wizardmath-70b-v1.0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of wizardlm_wizardmath-70b-v1.0 GGUF?

It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.1 GB and 4 more.

What context length does wizardlm_wizardmath-70b-v1.0 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download wizardlm_wizardmath-70b-v1.0 GGUF?

The files are on Hugging Face in the TheBloke/WizardMath-70B-V1.0-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 wizardlm_wizardmath-70b-v1.0 use?

Hugging Face lists the license as llama2. 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 WizardMath 70B V1.0 on 8 GB VRAM?

Use the Q4_K quantised file; it requires about 42.1 GB of VRAM at 8k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the llama2 license.

Other GGUFs of WizardMath-70B-V1.0

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Wizardmath models

All Wizardmath →

Other large models

All large models →