Knight Mixtral WizardLM 140B MoE i1 needs about 39.5 GB of memory at IQ2_XXS (a 37.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 29.0 GB (IQ1_S) to 45.8 GB (IQ2_M). Longer context needs more: at 32K tokens the KV cache alone adds about 7.4 GB.
Knight Mixtral WizardLM 140B MoE i1 is a 138B-parameter Mistral model in GGUF format, quantized by mradermacher. Its trained context length is 64K tokens. The repository has 6 quant files, from 29.0 GB (IQ1_S) to 45.8 GB (IQ2_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 29.0 GB | 31.4 GB | Too big | Get file → | |
| IQ1_M | 32.1 GB | 34.4 GB | Too big | Get file → | |
| IQ2_XXS | 37.2 GB | 39.5 GB | Too big | Get file → | |
| IQ2_XS | 41.2 GB | 43.6 GB | Too big | Get file → | |
| IQ2_S | 41.7 GB | 44.1 GB | Too big | Get file → | |
| IQ2_M | 45.8 GB | 48.2 GB | Too big | Get file → |
What GPU do you need for Knight Mixtral WizardLM 140B MoE i1?
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 (29.0 GB file, about 31.4 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_S (41.7 GB file, about 44.1 GB in use).
Which Knight Mixtral WizardLM 140B MoE i1 quant should you choose?
IQ2_XXS (37.2 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 29.0 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
Frequently asked questions about Knight Mixtral WizardLM 140B MoE i1
How much VRAM does Knight Mixtral WizardLM 140B MoE i1 need?
About 39.5 GB at IQ2_XXS with an 8K context window. That is the 37.2 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 Knight Mixtral WizardLM 140B MoE i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 31.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Knight Mixtral WizardLM 140B MoE i1 GGUF?
It depends on the quant: IQ1_S is 29.0 GB, IQ1_M is 32.1 GB, IQ2_XXS is 37.2 GB, IQ2_XS is 41.2 GB, IQ2_S is 41.7 GB, IQ2_M is 45.8 GB.
What context length does Knight Mixtral WizardLM 140B MoE i1 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.8 GB at 8K and 7.4 GB at 32K.
Where can I download Knight Mixtral WizardLM 140B MoE i1 GGUF?
The files are on Hugging Face in the mradermacher/Knight-Mixtral-WizardLM-140B-MoE-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.