RO

router_160

RouterGGUF by jiayuan1Updated 2024-11-08
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

router_160 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.9 GB (Q4_K_M) to 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

router_160 is a 8.03B-parameter Router model in GGUF format, quantized by jiayuan1. Its trained context length is 128K tokens. The repository has 3 quant files, from 4.9 GB (Q4_K_M) to 16.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
F1616.1 GB 17.6 GB
Too big Get file →

What GPU do you need for router_160?

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: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which router_160 quant should you choose?

Q4_K_M is the usual starting point for router_160: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byjiayuan1
FamilyRouter
Downloads (HF)13
Last updated2024-11-08

Frequently asked questions about router_160

How much VRAM does router_160 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 router_160 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of router_160 GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, Q5_K_M is 5.7 GB, F16 is 16.1 GB.

What context length does router_160 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 router_160 GGUF?

The files are on Hugging Face in the jiayuan1/router_160 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 jiayuan1

All by jiayuan1 →

More Router models

All Router →

Other small models

All small models →