BI

bitnet b1 58 3b q2 k stock

BitnetGGUF by AndreftyUpdated 2024-08-21
Download on Hugging Face
Parameters3.32B
Context2K
Layers—
Architecturebitnet
Smallest quant1.9 GB
Quick answer

bitnet b1 58 3b q2 k stock needs about 2.7 GB of memory at Q2_K (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU.

bitnet b1 58 3b q2 k stock is a 3.32B-parameter Bitnet model in GGUF format, quantized by Andrefty. Its trained context length is 2K tokens. The repository has 1 quant file, from 1.9 GB (Q2_K) to 1.9 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 2.5 GB
Fits Get file →

What GPU do you need for bitnet b1 58 3b q2 k stock?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q2_K (1.9 GB file, about 2.7 GB in use).

Which bitnet b1 58 3b q2 k stock quant should you choose?

Q2_K (1.9 GB) is the middle option in this repository. 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

Architecturebitnet
Parameters3.32B
Trained context2,048 tokens

Source

Quantized byAndrefty
FamilyBitnet
Downloads (HF)0
Last updated2024-08-21

Frequently asked questions about bitnet b1 58 3b q2 k stock

How much VRAM does bitnet b1 58 3b q2 k stock need?

About 2.7 GB at Q2_K with an 8K context window. That is the 1.9 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 bitnet b1 58 3b q2 k stock on an 8 GB GPU?

Yes, with Q2_K: the 1.9 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bitnet b1 58 3b q2 k stock GGUF?

It depends on the quant: Q2_K is 1.9 GB.

What context length does bitnet b1 58 3b q2 k stock support?

The GGUF header lists a trained context length of 2,048 tokens (2K).

Where can I download bitnet b1 58 3b q2 k stock GGUF?

The files are on Hugging Face in the Andrefty/bitnet_b1_58-3b-q2_k_stock 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 Bitnet models

All Bitnet →

Other tiny models

All tiny models →