BI

1bitLLM/bitnet_b1_58-large

BitllmGGUF by patrik-lambertUpdated 2025-10-14
Download on Hugging Face
Parameters729M
Context2K
Layers24
Architecturebitnet
Smallest quant0.2 GB
Quick answer

1bitLLM/bitnet_b1_58-large needs about 1.9 GB of memory at TQ2_0 (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.2 GB (TQ2_0) to 2.9 GB (F32).

1bitLLM/bitnet_b1_58-large is a 729M-parameter Bitllm model in GGUF format, quantized by patrik-lambert. Its trained context length is 2K tokens. The repository has 2 quant files, from 0.2 GB (TQ2_0) to 2.9 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ2_00.2 GB 1.0 GB
Fits Get file →
F322.9 GB 3.7 GB
Fits Get file →

What GPU do you need for 1bitLLM/bitnet_b1_58-large?

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: the best quant that fits is TQ2_0 (0.2 GB file, about 1.9 GB in use).
  • 6 GB VRAM: the best quant that fits is F32 (2.9 GB file, about 4.6 GB in use).

Which 1bitLLM/bitnet_b1_58-large quant should you choose?

TQ2_0 (0.2 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebitnet
Parameters729M
Layers24
Trained context2,048 tokens
KV cache (fp16)144 KB per token

Source

Quantized bypatrik-lambert
FamilyBitllm
Licensemit
Downloads (HF)23
Last updated2025-10-14

Frequently asked questions about 1bitLLM/bitnet_b1_58-large

How much VRAM does 1bitLLM/bitnet_b1_58-large need?

About 1.9 GB at TQ2_0 with an 8K context window. That is the 0.2 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 1bitLLM/bitnet_b1_58-large on an 8 GB GPU?

Yes, with F32: the 2.9 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of 1bitLLM/bitnet_b1_58-large GGUF?

It depends on the quant: TQ2_0 is 0.2 GB, F32 is 2.9 GB.

What context length does 1bitLLM/bitnet_b1_58-large support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.2 GB at 8K and 0.3 GB at 2K.

Where can I download 1bitLLM/bitnet_b1_58-large GGUF?

The files are on Hugging Face in the patrik-lambert/1bitLLM-bitnet_b1_58-large-f32.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 1bitLLM/bitnet_b1_58-large use?

Hugging Face lists the license as mit. 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 Bitllm models

All Bitllm →

Other tiny models

All tiny models →