AS

a1 v002

AshercnGGUF by ashercn97Updated 2024-11-29
Download on Hugging Face
Parameters7.62B
Context128K
Layers28
Architectureqwen2
Smallest quant4.7 GB
Quick answer

a1 v002 needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

a1 v002 is a 7.62B-parameter Ashercn model in GGUF format, quantized by ashercn97. Its trained context length is 128K tokens. The repository has 1 quant file, from 4.7 GB (Q4_K_M) to 4.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.7 GB 5.7 GB
Fits Get file →

What GPU do you need for a1 v002?

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: the best quant that fits is Q4_K_M (4.7 GB file, about 5.7 GB in use).

Which a1 v002 quant should you choose?

Q4_K_M is the usual starting point for a1 v002: it balances file size and quality well. Here it is a 4.7 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters7.62B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized byashercn97
FamilyAshercn
Licenseapache-2.0
Downloads (HF)34
Last updated2024-11-29

Frequently asked questions about a1 v002

How much VRAM does a1 v002 need?

About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 a1 v002 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.7 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of a1 v002 GGUF?

It depends on the quant: Q4_K_M is 4.7 GB.

What context length does a1 v002 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download a1 v002 GGUF?

The files are on Hugging Face in the ashercn97/a1-v002-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 a1 v002 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from ashercn97

All by ashercn97 →

More Ashercn models

All Ashercn →

Other small models

All small models →