WI

gguf sharded smashed WizardLM 2 7B

WizardlmGGUF by FelladrinUpdated 2024-05-14
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

gguf sharded smashed WizardLM 2 7B needs about 4.3 GB of memory at Q2_K (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

gguf sharded smashed WizardLM 2 7B is a 7.24B-parameter Wizardlm model in GGUF format, quantized by Felladrin. Its trained context length is 32K tokens. The repository has 1 quant file, from 2.7 GB (Q2_K) to 2.7 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB (45 parts) 4.3 GB
Fits Get file →

What GPU do you need for gguf sharded smashed WizardLM 2 7B?

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: the best quant that fits is Q2_K (2.7 GB file, about 4.3 GB in use).

Which gguf sharded smashed WizardLM 2 7B quant should you choose?

Q2_K (2.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byFelladrin
FamilyWizardlm
Downloads (HF)6
Last updated2024-05-14

Frequently asked questions about gguf sharded smashed WizardLM 2 7B

How much VRAM does gguf sharded smashed WizardLM 2 7B need?

About 4.3 GB at Q2_K with an 8K context window. That is the 2.7 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 gguf sharded smashed WizardLM 2 7B on an 8 GB GPU?

Yes, with Q2_K: the 2.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gguf sharded smashed WizardLM 2 7B GGUF?

It depends on the quant: Q2_K is 2.7 GB.

What context length does gguf sharded smashed WizardLM 2 7B 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 gguf sharded smashed WizardLM 2 7B GGUF?

The files are on Hugging Face in the Felladrin/gguf-sharded-smashed-WizardLM-2-7B 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 Felladrin

All by Felladrin →

More Wizardlm models

All Wizardlm →

Other small models

All small models →