LL

Llama3 35B lingyang v1 Q4 K M

LlamaGGUF by wwe180Updated 2024-05-30
Download on Hugging Face
Parameters35.5B
Context8K
Layers39
Architecturellama
Smallest quant21.4 GB
Quick answer

Llama3 35B lingyang v1 Q4 K M needs about 23.2 GB of memory at Q4_K_M (a 21.4 GB file) with an 8K context window, so it fits on a 24 GB GPU.

Llama3 35B lingyang v1 Q4 K M is a 35.5B-parameter Llama model in GGUF format, quantized by wwe180. Its trained context length is 8K tokens. The repository has 1 quant file, from 21.4 GB (Q4_K_M) to 21.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M21.4 GB 23.2 GB
Too big Get file →

What GPU do you need for Llama3 35B lingyang v1 Q4 K M?

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: the best quant that fits is Q4_K_M (21.4 GB file, about 23.2 GB in use).

Which Llama3 35B lingyang v1 Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Llama3 35B lingyang v1 Q4 K M: it balances file size and quality well. Here it is a 21.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters35.5B
Layers39
Trained context8,192 tokens
KV cache (fp16)156 KB per token

Source

Quantized bywwe180
FamilyLlama
Downloads (HF)25
Last updated2024-05-30

Frequently asked questions about Llama3 35B lingyang v1 Q4 K M

How much VRAM does Llama3 35B lingyang v1 Q4 K M need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 21.4 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 Llama3 35B lingyang v1 Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama3 35B lingyang v1 Q4 K M GGUF?

It depends on the quant: Q4_K_M is 21.4 GB.

What context length does Llama3 35B lingyang v1 Q4 K M support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.

Where can I download Llama3 35B lingyang v1 Q4 K M GGUF?

The files are on Hugging Face in the wwe180/Llama3-35B-lingyang-v1-Q4_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Llama3-35B-lingyang-v1

Similar models

Browse all →

More from wwe180

All by wwe180 →

More Llama models

All Llama →

Other large models

All large models →