LL

Llada22 Mini

LladaGGUF by DreamBloomsUpdated 2026-10-11
Download on Hugging Face
Parameters16.3B
Context128K
Layers20
Architecturellada2
Smallest quant9.9 GB
Quick answer

Llada22 Mini needs about 10.7 GB of memory at Q4_K_M (a 9.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 9.9 GB (Q4_K_M) to 17.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.

Llada22 Mini – 16.3B parameter agentic diffusion model

Llada22 Mini is a 16.3B parameter agentic diffusion model with a 131072 token context window. It supports reasoning and tool usage and is built on the llada2 architecture. The model is released under the Apache-2.0 license.

Good at

  • Long‑context reasoning
  • Tool calling
  • Multi‑turn interaction

Limits

  • Requires >10GB VRAM for Q4_K_M
  • No vision support
  • License is Apache-2.0

Best for

  • Chatbots needing long context
  • Tool‑enabled assistants
  • Debugging code with Levenshtein editing

Who it’s for. Developers building lightweight agentic assistants that need extended context and tool integration. The model is suitable for environments with moderate GPU memory and an Apache-2.0 compliant use case.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M9.9 GB 10.7 GB
Too big Get file →
Q8_017.3 GB 18.1 GB
Too big Get file →

For 12–16 GB VRAM, use the Q4_K_M quant (9.91 GB file, ~10.7 GB memory at 8 k context). If you have 20 GB or more, the Q8_0 quant (17.31 GB file, ~18.1 GB memory) provides higher precision.

What GPU do you need for Llada22 Mini?

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 Q4_K_M (9.9 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (9.9 GB file, about 10.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (17.3 GB file, about 18.1 GB in use).

Which Llada22 Mini quant should you choose?

Q4_K_M is the usual starting point for Llada22 Mini: it balances file size and quality well. Here it is a 9.9 GB file.

The Q8_0 file is 17.3 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellada2
Parameters16.3B (approximate, mixture of experts)
Layers20
Trained context131,072 tokens
KV cache (fp16)40 KB per token

Source

Quantized byDreamBlooms
FamilyLlada
Licenseapache-2.0
Downloads (HF)998
Last updated2026-10-11

Frequently asked questions about Llada22 Mini

How much VRAM does Llada22 Mini need?

About 10.7 GB at Q4_K_M with an 8K context window. That is the 9.9 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 Llada22 Mini 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 Llada22 Mini GGUF?

It depends on the quant: Q4_K_M is 9.9 GB, Q8_0 is 17.3 GB.

What context length does Llada22 Mini 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 1.3 GB at 32K.

Where can I download Llada22 Mini GGUF?

The files are on Hugging Face in the DreamBlooms/LLaDA2.2-mini-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 Llada22 Mini 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.

Can I run Llada22 Mini on 8 GB VRAM?

No. The smallest quant requires ~10.7 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does Llada22 Mini support vision?

No, the model does not include vision capabilities.

What license is Llada22 Mini released under?

Apache-2.0.

Similar models

Browse all →

More from DreamBlooms

All by DreamBlooms →

More Llada models

All Llada →

Other medium models

All medium models →