WI

WizardLM-2-8x22B

WizardlmGGUF by bartowskiUpdated 2024-04-17
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant52.1 GB
Quick answer

WizardLM-2-8x22B needs about 88.0 GB of memory at Q4_K_M (a 85.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 52.1 GB (Q2_K) to 100.0 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

WizardLM-2-8x22B – 141B parameter LLaMA‑style model

WizardLM-2-8x22B is a 141 billion‑parameter LLaMA‑based model with a 65 536‑token context window. It is released under the Apache‑2.0 license and is available in multiple GGUF quantizations. The model supports a wide range of languages and tasks.

Good at

  • Long‑form text generation
  • Complex reasoning
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM or RAM for high‑quality quants
  • License is Apache‑2.0

Best for

  • Research prototyping
  • Enterprise chatbot back‑ends
  • Content creation pipelines

Who it’s for. Engineers and researchers who need a large‑scale language model for advanced NLP tasks. The model is suitable for developers building applications that require extensive context and high‑quality text generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K52.1 GB (5 parts) 54.5 GB
Too big Get file →
IQ3_XS58.2 GB (5 parts) 60.6 GB
Too big Get file →
IQ3_S61.5 GB (5 parts) 63.9 GB
Too big Get file →
Q3_K_S61.5 GB (5 parts) 63.9 GB
Too big Get file →
IQ3_M64.5 GB (5 parts) 66.9 GB
Too big Get file →
Q3_K_M67.8 GB (5 parts) 70.2 GB
Too big Get file →
Q3_K_L72.6 GB (5 parts) 75.0 GB
Too big Get file →
IQ4_XS76.4 GB (5 parts) 78.7 GB
Too big Get file →
IQ4_NL80.5 GB (5 parts) 82.9 GB
Too big Get file →
Q4_K_S80.5 GB (5 parts) 82.9 GB
Too big Get file →
Q4_K_M85.6 GB (5 parts) 88.0 GB
Too big Get file →
Q5_K_S97.0 GB (5 parts) 99.4 GB
Too big Get file →
Q5_K_M100.0 GB (5 parts) 102.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (52.1 GB file, 54.5 GB memory at 8k context). For 16 GB VRAM, Q3_K_S (61.5 GB file, 63.9 GB memory) or IQ3_S (61.5 GB file, 63.9 GB memory). For 32 GB VRAM, Q4_K_M (85.59 GB file, 88 GB memory) or IQ4_NL (80.48 GB file, 82.9 GB memory).

What GPU do you need for WizardLM-2-8x22B?

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: no quant fits at an 8K context.

Which WizardLM-2-8x22B quant should you choose?

Q4_K_M is the usual starting point for WizardLM-2-8x22B: it balances file size and quality well. Here it is a 85.6 GB file.

If memory is tight, the smallest file is Q2_K at 52.1 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
Parameters141B (approximate, mixture of experts)
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized bybartowski
FamilyWizardlm
Licenseapache-2.0
Downloads (HF)437
Last updated2024-04-17

Frequently asked questions about WizardLM-2-8x22B

How much VRAM does WizardLM-2-8x22B need?

About 88.0 GB at Q4_K_M with an 8K context window. That is the 85.6 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-2-8x22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 54.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WizardLM-2-8x22B GGUF?

It depends on the quant: Q2_K is 52.1 GB, IQ3_XS is 58.2 GB, IQ3_S is 61.5 GB, Q3_K_S is 61.5 GB, IQ3_M is 64.5 GB, Q3_K_M is 67.8 GB and 7 more.

What context length does WizardLM-2-8x22B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download WizardLM-2-8x22B GGUF?

The files are on Hugging Face in the bartowski/WizardLM-2-8x22B-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-2-8x22B 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 WizardLM-2-8x22B on 8 GB VRAM?

Use the Q2_K quant, which has a 52.1 GB file size and requires about 54.5 GB of memory at 8k context. It will not fit on 8 GB VRAM alone.

What quant should I choose for 16 GB VRAM?

Choose Q3_K_S or IQ3_S, each 61.5 GB file and 63.9 GB memory at 8k context, which fits within 16 GB VRAM plus system RAM.

Is the model compatible with AMD GPUs?

I‑quants (IQ3, IQ4) work with rocBLAS on AMD, but are not compatible with the Vulkan build. K‑quants work on both Nvidia and AMD with the appropriate build.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Wizardlm models

All Wizardlm →

Other large models

All large models →