models--microsoft--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 14 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 GGUF model, 141 billion parameters
WizardLM‑2‑8x22B is a 141 billion‑parameter Llama‑style model released under Apache‑2.0. It supports a 65 536‑token context window and is available in multiple GGUF quantizations. The model is hosted on Hugging Face under the MaziyarPanahi/WizardLM‑2‑8x22B‑GGUF repository.
Good at
- Large context reasoning
- High‑capacity language modeling
- Fine‑tuned for general dialogue
Limits
- Requires high VRAM for large quants
- No vision capabilities
- No specialized licensing beyond Apache‑2.0
Best for
- Research on long‑form text generation
- Building custom chatbots with extended context
- Fine‑tuning for domain‑specific knowledge
Who it’s for. Developers and researchers needing a large‑scale language model with a 65 k token context. Suitable for environments that can accommodate the memory demands of the higher‑quality quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 29.6 GB | 32.0 GB | Too big | Get file → | |
| IQ1_M | 32.7 GB | 35.1 GB | Too big | Get file → | |
| Q2_K | 52.1 GB (5 parts) | 54.5 GB | Too big | Get file → | |
| IQ3_XS | 58.2 GB (5 parts) | 60.6 GB | Too big | Get file → | |
| Q3_K_S | 61.5 GB (5 parts) | 63.9 GB | Too big | Get file → | |
| Q3_K_M | 67.8 GB (5 parts) | 70.2 GB | Too big | Get file → | |
| Q3_K_L | 72.6 GB (5 parts) | 75.0 GB | Too big | Get file → | |
| IQ4_XS | 76.4 GB (5 parts) | 78.7 GB | Too big | Get file → | |
| Q4_K_S | 80.5 GB (5 parts) | 82.9 GB | Too big | Get file → | |
| Q4_K_M | 85.6 GB (5 parts) | 88.0 GB | Too big | Get file → | |
| Q5_K_S | 97.0 GB (5 parts) | 99.4 GB | Too big | Get file → | |
| Q5_K_M | 100.0 GB (5 parts) | 102.3 GB | Too big | Get file → | |
| Q6_K | 115.5 GB (5 parts) | 117.9 GB | Too big | Get file → | |
| Q8_0 | 149.4 GB (5 parts) | 151.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (32 GB memory estimate) or IQ1_M (35.1 GB). With 16 GB VRAM, Q2_K (54.5 GB) or Q3_K_S (63.9 GB) are feasible. For 32 GB VRAM, Q4_K_M (88 GB) or Q5_K_S (99.4 GB) provide better quality. Memory estimates are approximate.
What GPU do you need for models--microsoft--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: 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 IQ1_M (32.7 GB file, about 35.1 GB in use).
Which models--microsoft--WizardLM-2-8x22B quant should you choose?
Q4_K_M is the usual starting point for models--microsoft--WizardLM-2-8x22B: 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
Source
Frequently asked questions about models--microsoft--WizardLM-2-8x22B
How much VRAM does models--microsoft--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 models--microsoft--WizardLM-2-8x22B 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 models--microsoft--WizardLM-2-8x22B GGUF?
It depends on the quant: IQ1_S is 29.6 GB, IQ1_M is 32.7 GB, Q2_K is 52.1 GB, IQ3_XS is 58.2 GB, Q3_K_S is 61.5 GB, Q3_K_M is 67.8 GB and 8 more.
What context length does models--microsoft--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 models--microsoft--WizardLM-2-8x22B GGUF?
The files are on Hugging Face in the MaziyarPanahi/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 models--microsoft--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?
No, the smallest quant requires at least 32 GB of VRAM. Use a smaller model instead.
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 Apache‑2.0 license.