BO

BoulderTrain

BouldertrainGGUF by jk-hostingUpdated 2026-04-13
Download on Hugging Face
Parameters1.46B
Context1024K
Layers32
Architecturegranitehybrid
Smallest quant0.2 GB
Quick answer

BoulderTrain needs about 2.2 GB of memory at IQ4_NL (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.2 GB (IQ4_NL) to 1.9 GB (IQ4_NL). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

BoulderTrain is a 1.46B-parameter Bouldertrain model in GGUF format, quantized by jk-hosting. Its trained context length is 1024K tokens. The repository has 3 quant files, from 0.2 GB (IQ4_NL) to 1.9 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL0.2 GB 1.5 GB
Fits Get file →
IQ4_NL0.9 GB 2.2 GB
Fits Get file →
IQ4_NL1.9 GB 3.2 GB
Fits Get file →

What GPU do you need for BoulderTrain?

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 IQ4_NL (1.9 GB file, about 3.2 GB in use).

Which BoulderTrain quant should you choose?

IQ4_NL (0.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ4_NL at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranitehybrid
Parameters1.46B
Layers32
Trained context1,048,576 tokens
KV cache (fp16)96 KB per token

Source

Quantized byjk-hosting
Licenseapache-2.0
Downloads (HF)11
Last updated2026-04-13

Frequently asked questions about BoulderTrain

How much VRAM does BoulderTrain need?

About 2.2 GB at IQ4_NL with an 8K context window. That is the 0.9 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 BoulderTrain on an 8 GB GPU?

Yes, with IQ4_NL: the 1.9 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of BoulderTrain GGUF?

It depends on the quant: IQ4_NL is 0.2 GB, IQ4_NL is 0.9 GB, IQ4_NL is 1.9 GB.

What context length does BoulderTrain support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download BoulderTrain GGUF?

The files are on Hugging Face in the jk-hosting/BoulderTrain repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does BoulderTrain use?

Hugging Face lists the license as apache-2.0. 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 →

Other tiny models

All tiny models →