NE

new05B

NewGGUF by 1bconvertUpdated 2026-06-15
Download on Hugging Face
Parameters354M
Context125K
Layers16
Architecturelfm2
Smallest quant0.2 GB
Quick answer

new05B needs about 1.3 GB of memory at Q4_K_M (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 (Q4_K_M) to 0.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

new05B is a 354M-parameter New model in GGUF format, quantized by 1bconvert. Its trained context length is 125K tokens. The repository has 2 quant files, from 0.2 GB (Q4_K_M) to 0.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.2 GB 1.3 GB
Fits Get file →
Q4_K_M0.5 GB 1.6 GB
Fits Get file →

What GPU do you need for new05B?

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 Q4_K_M (0.5 GB file, about 1.6 GB in use).

Which new05B quant should you choose?

Q4_K_M is the usual starting point for new05B: it balances file size and quality well. Here it is a 0.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters354M
Layers16
Trained context128,000 tokens
KV cache (fp16)64 KB per token

Source

Quantized by1bconvert
FamilyNew
Licenseother
Downloads (HF)20
Last updated2026-06-15

Frequently asked questions about new05B

How much VRAM does new05B need?

About 1.3 GB at Q4_K_M 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 new05B on an 8 GB GPU?

Yes, with Q4_K_M: the 0.5 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of new05B GGUF?

It depends on the quant: Q4_K_M is 0.2 GB, Q4_K_M is 0.5 GB.

What context length does new05B support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download new05B GGUF?

The files are on Hugging Face in the 1bconvert/new05Bgguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does new05B use?

Hugging Face lists the license as other. 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 1bconvert

All by 1bconvert →

More New models

All New →

Other tiny models

All tiny models →