HA

Hajax_Chat_1.0

HajaxGGUF by Tech-MeldUpdated 2024-06-12
Download on Hugging Face
Parameters7.24B
Context8K
Layers32
Architecturellama
Smallest quant3.2 GB
Quick answer

Hajax_Chat_1.0 needs about 4.7 GB of memory at Q3_K_S (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU.

Hajax_Chat_1.0 is a 7.24B-parameter Hajax model in GGUF format, quantized by Tech-Meld. Its trained context length is 8K tokens. The repository has 1 quant file, from 3.2 GB (Q3_K_S) to 3.2 GB (Q3_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S3.2 GB 4.7 GB
Fits Get file →

What GPU do you need for Hajax_Chat_1.0?

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: the best quant that fits is Q3_K_S (3.2 GB file, about 4.7 GB in use).

Which Hajax_Chat_1.0 quant should you choose?

Q3_K_S (3.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byTech-Meld
FamilyHajax
Downloads (HF)26
Last updated2024-06-12

Frequently asked questions about Hajax_Chat_1.0

How much VRAM does Hajax_Chat_1.0 need?

About 4.7 GB at Q3_K_S with an 8K context window. That is the 3.2 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 Hajax_Chat_1.0 on an 8 GB GPU?

Yes, with Q3_K_S: the 3.2 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hajax_Chat_1.0 GGUF?

It depends on the quant: Q3_K_S is 3.2 GB.

What context length does Hajax_Chat_1.0 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 Hajax_Chat_1.0 GGUF?

The files are on Hugging Face in the Tech-Meld/Hajax_Chat_1.0-Q3_K_S-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 Hajax_Chat_1.0

Similar models

Browse all →

More from Tech-Meld

All by Tech-Meld →

More Hajax models

All Hajax →

Other small models

All small models →