KA

Kanana 2 30B A3B Instruct

KananaGGUF by ohora23Updated 2026-07-06
Download on Hugging Face
Parameters30.7B
Context32K
Layers48
Architecturedeepseek2
Smallest quant18.6 GB
Quick answer

Kanana 2 30B A3B Instruct needs about 20.0 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.4 GB.

Kanana 2 30B A3B Instruct – 30.7B parameter model with MoE and 32,768 token context

Kanana 2 30B A3B Instruct is a 30.7B parameter model built on deepseek2 architecture with MLA and MoE. It supports up to 32,768 token context and focuses on reasoning and tool usage. The model is distributed as a GGUF Q4_K_M quantization.

Good at

  • Reasoning
  • Tool calling
  • Instruction following

Limits

  • Requires ~20 GB VRAM at 8k context
  • No vision support
  • License is other

Best for

  • Long‑context reasoning
  • Agentic tool‑calling workflows
  • Complex instruction following

Who it’s for. Developers and researchers building agentic AI systems that need large‑context reasoning and tool integration on consumer hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M18.6 GB 20.0 GB
Too big Get file →

The only available quant is Q4_K_M with a file size of 18.6 GB and an estimated memory usage of 20 GB at 8k context. For 8k context this is the recommended quant. If your GPU has less than 20 GB VRAM, the model will not run efficiently.

What GPU do you need for Kanana 2 30B A3B 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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (18.6 GB file, about 20.0 GB in use).

Which Kanana 2 30B A3B Instruct quant should you choose?

Q4_K_M is the usual starting point for Kanana 2 30B A3B Instruct: it balances file size and quality well. Here it is a 18.6 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2
Parameters30.7B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context32,768 tokens
KV cache (fp16)102 KB per token

Source

Quantized byohora23
FamilyKanana
Licenseother
Downloads (HF)635
Last updated2026-07-06

Frequently asked questions about Kanana 2 30B A3B Instruct

How much VRAM does Kanana 2 30B A3B Instruct need?

About 20.0 GB at Q4_K_M with an 8K context window. That is the 18.6 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 Kanana 2 30B A3B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kanana 2 30B A3B Instruct GGUF?

It depends on the quant: Q4_K_M is 18.6 GB.

What context length does Kanana 2 30B A3B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.4 GB at 32K.

Where can I download Kanana 2 30B A3B Instruct GGUF?

The files are on Hugging Face in the ohora23/Kanana-2-30B-A3B-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 Kanana 2 30B A3B Instruct use?

Hugging Face lists the license as other. 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 Kanana 2 30B A3B Instruct on 8 GB VRAM?

No, the Q4_K_M quant requires approximately 20 GB VRAM at 8k context, so 8 GB is insufficient.

Does the model support 32,768 token context?

Yes, the model was trained with a 32,768 token context length.

Is there vision support?

No, the model does not support vision capabilities.

Other GGUFs of kanana-2-30b-a3b-instruct-2601

Similar models

Browse all →

More Kanana models

All Kanana →

Other medium models

All medium models →