LL

LLaMa-3-Stheno-v3.2-15B

LlamaGGUF by Lancer1408Updated 2024-07-15
Download on Hugging Face
Parameters15B
Context8K
Layers64
Architecturellama
Smallest quant10.7 GB
Quick answer

LLaMa-3-Stheno-v3.2-15B needs about 13.3 GB of memory at Q5_K_M (a 10.7 GB file) with an 8K context window, so it fits on a 16 GB GPU.

LLaMa-3-Stheno-v3.2-15B is a 15B-parameter Llama model in GGUF format, quantized by Lancer1408. Its trained context length is 8K tokens. The repository has 1 quant file, from 10.7 GB (Q5_K_M) to 10.7 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M10.7 GB 13.3 GB
Too big Get file →

What GPU do you need for LLaMa-3-Stheno-v3.2-15B?

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: the best quant that fits is Q5_K_M (10.7 GB file, about 13.3 GB in use).

Which LLaMa-3-Stheno-v3.2-15B quant should you choose?

Q5_K_M (10.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters15B
Layers64
Trained context8,192 tokens
KV cache (fp16)256 KB per token

Source

Quantized byLancer1408
FamilyLlama
Downloads (HF)35
Last updated2024-07-15

Frequently asked questions about LLaMa-3-Stheno-v3.2-15B

How much VRAM does LLaMa-3-Stheno-v3.2-15B need?

About 13.3 GB at Q5_K_M with an 8K context window. That is the 10.7 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 LLaMa-3-Stheno-v3.2-15B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LLaMa-3-Stheno-v3.2-15B GGUF?

It depends on the quant: Q5_K_M is 10.7 GB.

What context length does LLaMa-3-Stheno-v3.2-15B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.

Where can I download LLaMa-3-Stheno-v3.2-15B GGUF?

The files are on Hugging Face in the Lancer1408/LLaMa-3-Stheno-v3.2-15B-Q5_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 LLaMa-3-Stheno-v3.2-15B

Similar models

Browse all →

More Llama models

All Llama →

Other medium models

All medium models →