BA

Bahasa 4b chat f32

BahasaGGUF by lock-rrUpdated 2024-05-16
Download on Hugging Face
Parameters3.95B
Context32K
Layers40
Architecturellama
Smallest quant15.8 GB
Quick answer

Bahasa 4b chat f32 needs about 19.7 GB of memory at F32 (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.

Bahasa 4b chat f32 is a 3.95B-parameter Bahasa model in GGUF format, quantized by lock-rr. Its trained context length is 32K tokens. The repository has 1 quant file, from 15.8 GB (F32) to 15.8 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F3215.8 GB 19.7 GB
Too big Get file →

What GPU do you need for Bahasa 4b chat f32?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is F32 (15.8 GB file, about 19.7 GB in use).

Which Bahasa 4b chat f32 quant should you choose?

F32 (15.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.95B
Layers40
Trained context32,768 tokens
KV cache (fp16)400 KB per token

Source

Quantized bylock-rr
FamilyBahasa
Downloads (HF)8
Last updated2024-05-16

Frequently asked questions about Bahasa 4b chat f32

How much VRAM does Bahasa 4b chat f32 need?

About 19.7 GB at F32 with an 8K context window. That is the 15.8 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 Bahasa 4b chat f32 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bahasa 4b chat f32 GGUF?

It depends on the quant: F32 is 15.8 GB.

What context length does Bahasa 4b chat f32 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.4 GB at 32K.

Where can I download Bahasa 4b chat f32 GGUF?

The files are on Hugging Face in the lock-rr/Bahasa-4b-chat-f32.gguf 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 lock-rr

All by lock-rr →

More Bahasa models

All Bahasa →

Other small models

All small models →