WI

WizardLM 2 8x22B iMat

WizardlmGGUF by InferenceIllusionistUpdated 2024-06-15
Download on Hugging Face
Parameters141B
Context64K
Layers56
Architecturellama
Smallest quant29.6 GB
Quick answer

WizardLM 2 8x22B iMat 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 18 quants, from 29.6 GB (IQ1_S) to 115.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

WizardLM 2 8x22B iMat is a 141B-parameter Wizardlm model in GGUF format, quantized by InferenceIllusionist. Its trained context length is 64K tokens. The repository has 18 quant files, from 29.6 GB (IQ1_S) to 115.5 GB (Q6_K).

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 (3 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 →
IQ3_M64.5 GB (3 parts) 66.9 GB
Too big Get file →
Q3_K_M67.8 GB (2 parts) 70.2 GB
Too big Get file →
IQ4_XS75.5 GB (2 parts) 77.9 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 →
Q5_K_S97.0 GB (3 parts) 99.4 GB
Too big Get file →
Q5_K_M100.0 GB (3 parts) 102.4 GB
Too big Get file →
Q6_K115.5 GB (3 parts) 117.9 GB
Too big Get file →

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

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 iMat quant should you choose?

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

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

FamilyWizardlm
Downloads (HF)419
Last updated2024-06-15

Frequently asked questions about WizardLM 2 8x22B iMat

How much VRAM does WizardLM 2 8x22B iMat 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 iMat 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 iMat 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 12 more.

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

The files are on Hugging Face in the InferenceIllusionist/WizardLM-2-8x22B-iMat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from InferenceIllusionist

All by InferenceIllusionist →

More Wizardlm models

All Wizardlm →

Other large models

All large models →