LL

LLaMA Pro 8B

LlamaGGUF by mradermacherUpdated 2024-11-15
Download on Hugging Face
Parameters8.36B
Context4K
Layers40
Architecturellama
Smallest quant3.1 GB
Quick answer

LLaMA Pro 8B needs about 10.9 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 13 quants, from 3.1 GB (Q2_K) to 16.7 GB (F16).

LLaMA Pro 8B is a 8.36B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 13 quant files, from 3.1 GB (Q2_K) to 16.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 6.3 GB
Fits Get file →
Q3_K_S3.6 GB 6.8 GB
Fits Get file →
Q3_K_M4.1 GB 7.3 GB
Tight Get file →
Q3_K_L4.5 GB 7.6 GB
Tight Get file →
IQ4_XS4.5 GB 7.7 GB
Tight Get file →
Q4_04.7 GB 7.9 GB
Tight Get file →
Q4_K_S4.8 GB 8.0 GB
Tight Get file →
Q4_K_M5.1 GB 8.2 GB
Too big Get file →
Q5_K_S5.8 GB 8.9 GB
Too big Get file →
Q5_K_M5.9 GB 9.1 GB
Too big Get file →
Q6_K6.9 GB 10.0 GB
Too big Get file →
Q8_08.9 GB 12.1 GB
Too big Get file →
F1616.7 GB 19.9 GB
Too big Get file →

What GPU do you need for LLaMA Pro 8B?

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 Q5_K_M (5.9 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.9 GB file, about 14.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.7 GB file, about 22.6 GB in use).

Which LLaMA Pro 8B quant should you choose?

Q4_K_M is the usual starting point for LLaMA Pro 8B: it balances file size and quality well. Here it is a 5.1 GB file.

The Q8_0 file is 8.9 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 3.1 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
Parameters8.36B
Layers40
Trained context4,096 tokens
KV cache (fp16)640 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama2
Downloads (HF)313
Last updated2024-11-15

Frequently asked questions about LLaMA Pro 8B

How much VRAM does LLaMA Pro 8B need?

About 10.9 GB at Q4_K_M with an 8K context window. That is the 5.1 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 Pro 8B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LLaMA Pro 8B GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.6 GB, Q3_K_M is 4.1 GB, Q3_K_L is 4.5 GB, IQ4_XS is 4.5 GB, Q4_0 is 4.7 GB and 7 more.

What context length does LLaMA Pro 8B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 5.4 GB at 8K and 2.7 GB at 4K.

Where can I download LLaMA Pro 8B GGUF?

The files are on Hugging Face in the mradermacher/LLaMA-Pro-8B-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 LLaMA Pro 8B use?

Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of LLaMA-Pro-8B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →