LL

las model 120c

LlasaGGUF by fqbUpdated 2025-05-19
Download on Hugging Face
Parameters1.37B
Context128K
Layers16
Architecturellama
Smallest quant0.9 GB
Quick answer

las model 120c needs about 1.7 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

las model 120c is a 1.37B-parameter Llasa model in GGUF format, quantized by fqb. Its trained context length is 128K tokens. The repository has 1 quant file, from 0.9 GB (Q4_K_M) to 0.9 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.9 GB 1.7 GB
Fits Get file →

What GPU do you need for las model 120c?

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 (0.9 GB file, about 1.7 GB in use).

Which las model 120c quant should you choose?

Q4_K_M is the usual starting point for las model 120c: it balances file size and quality well. Here it is a 0.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.37B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized byfqb
FamilyLlasa
Licenseapache-2.0
Downloads (HF)25
Last updated2025-05-19

Frequently asked questions about las model 120c

How much VRAM does las model 120c need?

About 1.7 GB at Q4_K_M 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 las model 120c on an 8 GB GPU?

Yes, with Q4_K_M: the 0.9 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of las model 120c GGUF?

It depends on the quant: Q4_K_M is 0.9 GB.

What context length does las model 120c support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download las model 120c GGUF?

The files are on Hugging Face in the fqb/las_model_120c_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 las model 120c 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.

Other GGUFs of Llasa-1B-Multilingual

Similar models

Browse all →

More from fqb

All by fqb →

More Llasa models

All Llasa →

Other tiny models

All tiny models →