LL

merged meta llama lora bf16 Q8 0

LlamaGGUF by lovellmnotUpdated 2024-09-15
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant8.5 GB
Quick answer

merged meta llama lora bf16 Q8 0 needs about 10.1 GB of memory at BF16 (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU.

merged meta llama lora bf16 Q8 0 is a 8.03B-parameter Llama model in GGUF format, quantized by lovellmnot. Its trained context length is 8K tokens. The repository has 1 quant file, from 8.5 GB (BF16) to 8.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF168.5 GB 10.1 GB
Too big Get file →

What GPU do you need for merged meta llama lora bf16 Q8 0?

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 BF16 (8.5 GB file, about 10.1 GB in use).

Which merged meta llama lora bf16 Q8 0 quant should you choose?

BF16 (8.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylovellmnot
FamilyLlama
Downloads (HF)9
Last updated2024-09-15

Frequently asked questions about merged meta llama lora bf16 Q8 0

How much VRAM does merged meta llama lora bf16 Q8 0 need?

About 10.1 GB at BF16 with an 8K context window. That is the 8.5 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 merged meta llama lora bf16 Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of merged meta llama lora bf16 Q8 0 GGUF?

It depends on the quant: BF16 is 8.5 GB.

What context length does merged meta llama lora bf16 Q8 0 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download merged meta llama lora bf16 Q8 0 GGUF?

The files are on Hugging Face in the lovellmnot/merged-meta-llama-lora-bf16-Q8_0-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 merged-meta-llama-lora-bf16

Similar models

Browse all →

More from lovellmnot

All by lovellmnot →

More Llama models

All Llama →

Other small models

All small models →