LA

lapa v0.1.2 instruct

LapaGGUF by lapa-llmUpdated 2026-03-14
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant6.9 GB
Quick answer

lapa v0.1.2 instruct needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 6.9 GB (Q4_K_S) to 23.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

lapa v0.1.2 instruct is a 11.8B-parameter Lapa model in GGUF format, quantized by lapa-llm. Its trained context length is 128K tokens. The repository has 5 quant files, from 6.9 GB (Q4_K_S) to 23.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S6.9 GB 10.7 GB
Too big Get file →
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q5_K_S8.2 GB 12.0 GB
Too big Get file →
Q8_012.5 GB 16.2 GB
Too big Get file →
BF1623.5 GB 27.3 GB
Too big Get file →

What GPU do you need for lapa v0.1.2 instruct?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (23.5 GB file, about 27.3 GB in use).

Which lapa v0.1.2 instruct quant should you choose?

Q4_K_M is the usual starting point for lapa v0.1.2 instruct: it balances file size and quality well. Here it is a 7.3 GB file.

The Q8_0 file is 12.5 GB, about 1.7 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.

If memory is tight, the smallest file is Q4_K_S at 6.9 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

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bylapa-llm
FamilyLapa
Licensegemma
Downloads (HF)490
Last updated2026-03-14

Frequently asked questions about lapa v0.1.2 instruct

How much VRAM does lapa v0.1.2 instruct need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 lapa v0.1.2 instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of lapa v0.1.2 instruct GGUF?

It depends on the quant: Q4_K_S is 6.9 GB, Q4_K_M is 7.3 GB, Q5_K_S is 8.2 GB, Q8_0 is 12.5 GB, BF16 is 23.5 GB.

What context length does lapa v0.1.2 instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download lapa v0.1.2 instruct GGUF?

The files are on Hugging Face in the lapa-llm/lapa-v0.1.2-instruct-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 lapa v0.1.2 instruct use?

Hugging Face lists the license as gemma. 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 Lapa models

All Lapa →

Other medium models

All medium models →