WI

WizardLM 2 4x7B MoE

WizardlmGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters24.2B
Context32K
Layers32
Architecturellama
Smallest quant8.8 GB
Quick answer

WizardLM 2 4x7B MoE needs about 16.2 GB of memory at Q4_K_M (a 14.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 14 quants, from 8.8 GB (Q2_K) to 25.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

WizardLM 2 4x7B MoE – 24.2B parameter mixture of experts

WizardLM 2 4x7B MoE is a 24.2B parameter model built from four WizardLM‑2‑7B models using Mergekit. It supports a 32768 token context window and is licensed under apache‑2.0. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Mixture of experts inference
  • Instruction following

Limits

  • No vision support
  • Requires 8k context for best results
  • No GPU‑only EXL2 quant available in GGUF

Best for

  • Long‑form content generation
  • Complex instruction execution
  • Research prototyping

Who it’s for. Developers and researchers needing a large‑parameter MoE model with extended context. Suitable for CPU‑heavy or mixed GPU+CPU inference environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.8 GB 10.4 GB
Too big Get file →
IQ3_XS9.9 GB 11.5 GB
Too big Get file →
Q3_K_S10.4 GB 12.0 GB
Too big Get file →
IQ3_S10.5 GB 12.0 GB
Too big Get file →
IQ3_M10.6 GB 12.2 GB
Too big Get file →
Q3_K_M11.6 GB 13.2 GB
Too big Get file →
Q3_K_L12.5 GB 14.1 GB
Too big Get file →
IQ4_XS13.0 GB 14.6 GB
Too big Get file →
Q4_K_S13.7 GB 15.3 GB
Too big Get file →
Q4_K_M14.6 GB 16.2 GB
Too big Get file →
Q5_K_S16.6 GB 18.2 GB
Too big Get file →
Q5_K_M17.1 GB 18.7 GB
Too big Get file →
Q6_K19.8 GB 21.4 GB
Too big Get file →
Q8_025.7 GB 27.2 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (8.84 GB file, ~10.4 GB memory at 8k context). For 12‑GB VRAM, Q3_K_L (12.54 GB file, ~14.1 GB memory). For 16‑GB VRAM, Q4_K_M (14.61 GB file, ~16.2 GB memory).

What GPU do you need for WizardLM 2 4x7B MoE?

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: the best quant that fits is IQ3_S (10.5 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (13.7 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.8 GB file, about 21.4 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (25.7 GB file, about 27.2 GB in use).

Which WizardLM 2 4x7B MoE quant should you choose?

Q4_K_M is the usual starting point for WizardLM 2 4x7B MoE: it balances file size and quality well. Here it is a 14.6 GB file.

The Q8_0 file is 25.7 GB, about 1.8 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 Q2_K at 8.8 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
Parameters24.2B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyWizardlm
Licenseapache-2.0
Downloads (HF)1,709
Last updated2024-05-06

Frequently asked questions about WizardLM 2 4x7B MoE

How much VRAM does WizardLM 2 4x7B MoE need?

About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.6 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 4x7B MoE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WizardLM 2 4x7B MoE GGUF?

It depends on the quant: Q2_K is 8.8 GB, IQ3_XS is 9.9 GB, Q3_K_S is 10.4 GB, IQ3_S is 10.5 GB, IQ3_M is 10.6 GB, Q3_K_M is 11.6 GB and 8 more.

What context length does WizardLM 2 4x7B MoE support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download WizardLM 2 4x7B MoE GGUF?

The files are on Hugging Face in the mradermacher/WizardLM-2-4x7B-MoE-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 4x7B MoE 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 4x7B MoE on 8 GB VRAM?

Yes, using the Q2_K quant which requires about 10.4 GB memory at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What instruction template is recommended?

Vicuna‑v1.1 is recommended for instruction templates.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Wizardlm models

All Wizardlm →

Other medium models

All medium models →