WI

WizardLM 2 8x22B imatrix

WizardlmGGUF by hermes42Updated 2024-06-01
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant29.6 GB
Quick answer

WizardLM 2 8x22B imatrix 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 25 quants, from 29.6 GB (IQ1_S) to 149.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

WizardLM 2 8x22B imatrix – 141B Mixture of Experts model

WizardLM 2 8x22B imatrix is a 141B parameter mixture of experts model based on the llama architecture. It supports 65536 context tokens and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Multilingual text generation
  • Tool‑use capability

Limits

  • Requires high VRAM for full precision
  • No vision support
  • Large model size

Best for

  • Complex chat applications
  • Multilingual content creation
  • Agent‑style tool usage

Who it’s for. Developers and researchers needing a large, multilingual language model with tool‑use support. Suitable for applications that can accommodate the model’s memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S29.6 GB 32.0 GB
Too big Get file →
IQ1_M32.7 GB 35.1 GB
Too big Get file →
IQ2_XXS37.9 GB 40.3 GB
Too big Get file →
IQ2_XS42.0 GB 44.4 GB
Too big Get file →
IQ2_S42.6 GB 45.0 GB
Too big Get file →
IQ2_M46.7 GB 49.1 GB
Too big Get file →
Q2_K52.1 GB (2 parts) 54.5 GB
Too big Get file →
IQ3_XXS54.9 GB (2 parts) 57.3 GB
Too big Get file →
IQ3_XS58.2 GB (2 parts) 60.6 GB
Too big Get file →
IQ3_S61.5 GB (2 parts) 63.9 GB
Too big Get file →
Q3_K_S61.5 GB (2 parts) 63.9 GB
Too big Get file →
IQ3_M64.5 GB (2 parts) 66.9 GB
Too big Get file →
Q3_K_M67.8 GB (2 parts) 70.2 GB
Too big Get file →
Q3_K_L72.6 GB (2 parts) 75.0 GB
Too big Get file →
IQ4_XS75.5 GB (2 parts) 77.9 GB
Too big Get file →
Q4_079.9 GB (2 parts) 82.2 GB
Too big Get file →
Q4_K_S80.5 GB (3 parts) 82.9 GB
Too big Get file →
Q4_K_M85.6 GB (3 parts) 88.0 GB
Too big Get file →
Q4_188.2 GB (3 parts) 90.6 GB
Too big Get file →
Q5_K_S97.0 GB (3 parts) 99.4 GB
Too big Get file →
Q5_097.3 GB (3 parts) 99.7 GB
Too big Get file →
Q5_K_M100.0 GB (3 parts) 102.4 GB
Too big Get file →
Q5_1105.7 GB (3 parts) 108.1 GB
Too big Get file →
Q6_K115.5 GB (3 parts) 117.9 GB
Too big Get file →
Q8_0149.4 GB (4 parts) 151.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (32 GB file, 32 GB memory at 8 k context). For 16 GB VRAM, IQ2_XS (42 GB file, 44.4 GB memory) or Q2_K (52.11 GB file, 54.5 GB memory). For 32 GB VRAM, Q4_K_M (85.59 GB file, 88 GB memory) or Q5_K_M (99.97 GB file, 102.4 GB memory).

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

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 IQ1_S (29.6 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_S (42.6 GB file, about 45.0 GB in use).

Which WizardLM 2 8x22B imatrix quant should you choose?

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

The Q8_0 file is 149.4 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 IQ1_S at 29.6 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 byhermes42
FamilyWizardlm
Licenseapache-2.0
Downloads (HF)1,601
Last updated2024-06-01

Frequently asked questions about WizardLM 2 8x22B imatrix

How much VRAM does WizardLM 2 8x22B imatrix 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 imatrix on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.0 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ1_S is 29.6 GB, IQ1_M is 32.7 GB, IQ2_XXS is 37.9 GB, IQ2_XS is 42.0 GB, IQ2_S is 42.6 GB, IQ2_M is 46.7 GB and 19 more.

What context length does WizardLM 2 8x22B imatrix 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 imatrix GGUF?

The files are on Hugging Face in the hermes42/WizardLM-2-8x22B-imatrix-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 imatrix 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 this model on 8 GB VRAM?

Only the IQ1_S quantization is feasible, requiring 32 GB file size and 32 GB memory at 8 k context, which exceeds 8 GB VRAM.

Does the model support vision tasks?

No, the model has no vision capability.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from hermes42

All by hermes42 →

More Wizardlm models

All Wizardlm →

Other large models

All large models →