HO

HobbyLM-1B (sft)

HobbylmGGUF by harims95Updated 2026-10-13
Download on Hugging Face
Parameters1.09B
Context4K
Layers20
Architecturebailingmoe2
Smallest quant0.7 GB
Quick answer

HobbyLM-1B (sft) needs about 1.9 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.7 GB (Q4_K_M) to 4.4 GB (F32).

HobbyLM-1B (sft) is a 1.09B-parameter Hobbylm model in GGUF format, quantized by harims95. Its trained context length is 4K tokens. The repository has 4 quant files, from 0.7 GB (Q4_K_M) to 4.4 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q8_01.2 GB 2.0 GB
Fits Get file →
F324.4 GB 5.2 GB
Fits Get file →
F324.4 GB 5.2 GB
Fits Get file →

What GPU do you need for HobbyLM-1B (sft)?

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 Q8_0 (1.2 GB file, about 2.3 GB in use).
  • 6 GB VRAM: the best quant that fits is F32 (4.4 GB file, about 5.5 GB in use).

Which HobbyLM-1B (sft) quant should you choose?

Q4_K_M is the usual starting point for HobbyLM-1B (sft): it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebailingmoe2
Parameters1.09B (approximate, mixture of experts)
Layers20
Trained context4,096 tokens
KV cache (fp16)80 KB per token

Source

Quantized byharims95
FamilyHobbylm
Licenseapache-2.0
Downloads (HF)317
Last updated2026-10-13

Frequently asked questions about HobbyLM-1B (sft)

How much VRAM does HobbyLM-1B (sft) need?

About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.7 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 HobbyLM-1B (sft) on an 8 GB GPU?

Yes, with F32: the 4.4 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of HobbyLM-1B (sft) GGUF?

It depends on the quant: Q4_K_M is 0.7 GB, Q8_0 is 1.2 GB, F32 is 4.4 GB, F32 is 4.4 GB.

What context length does HobbyLM-1B (sft) support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.3 GB at 4K.

Where can I download HobbyLM-1B (sft) GGUF?

The files are on Hugging Face in the harims95/hobbylm-1B-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 HobbyLM-1B (sft) 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 →

More Hobbylm models

All Hobbylm →

Other tiny models

All tiny models →