KA

Kanana 1.5 15.7b A3B Instruct

KananaGGUF by mradermacherUpdated 2025-12-18
Download on Hugging Face
Parameters15.7B
Context32K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

Kanana 1.5 15.7b A3B Instruct needs about 12.0 GB of memory at Q4_K_M (a 10.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 14.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Kanana 1.5 15.7b A3B Instruct – a Mixture‑of‑Experts Llama model

Kanana 1.5 15.7b A3B Instruct is a 15.7 b parameter Llama‑style model with sparse MoE architecture. It supports 32 768 token context and includes tools capability. The model is available in multiple GGUF quantizations.

Good at

  • Tools execution
  • Large context reasoning
  • Efficient inference

Limits

  • No vision support
  • License is other
  • Requires 8 k context for memory estimates

Best for

  • Chatbot with tool use
  • Long‑form content generation
  • Code assistance

Who it’s for. Developers and researchers needing a large‑scale Llama model with MoE efficiency. Suitable for applications that can leverage tools and long context windows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S5.1 GB 6.6 GB
Fits Get file →
IQ1_M5.3 GB 6.9 GB
Fits Get file →
IQ2_XXS5.7 GB 7.3 GB
Tight Get file →
IQ2_XS6.0 GB 7.6 GB
Tight Get file →
IQ2_S6.1 GB 7.7 GB
Tight Get file →
IQ2_M6.4 GB 8.0 GB
Tight Get file →
Q2_K6.5 GB 8.1 GB
Too big Get file →
Q2_K_S6.5 GB 8.1 GB
Too big Get file →
IQ3_XXS7.0 GB 8.6 GB
Too big Get file →
IQ3_XS7.2 GB 8.7 GB
Too big Get file →
Q3_K_S7.5 GB 9.1 GB
Too big Get file →
IQ3_S7.5 GB 9.1 GB
Too big Get file →
IQ3_M7.6 GB 9.2 GB
Too big Get file →
Q3_K_M8.2 GB 9.8 GB
Too big Get file →
Q3_K_L8.5 GB 10.1 GB
Too big Get file →
IQ4_XS8.6 GB 10.2 GB
Too big Get file →
IQ4_NL8.9 GB 10.5 GB
Too big Get file →
Q4_09.0 GB 10.5 GB
Too big Get file →
Q4_K_S9.6 GB 11.1 GB
Too big Get file →
Q4_19.9 GB 11.5 GB
Too big Get file →
Q4_K_M10.4 GB 12.0 GB
Too big Get file →
Q5_K_S11.2 GB 12.7 GB
Too big Get file →
Q5_K_M11.9 GB 13.5 GB
Too big Get file →
Q6_K14.1 GB 15.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 10.44 GB, ~12 GB memory at 8 k context). For 16 GB VRAM, Q5_K_M (11.91 GB, ~13.5 GB). For 32 GB VRAM, Q6_K (14.07 GB, ~15.6 GB). Estimates are approximate.

What GPU do you need for Kanana 1.5 15.7b 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: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_M (6.4 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (10.4 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (14.1 GB file, about 15.6 GB in use).

Which Kanana 1.5 15.7b A3B Instruct quant should you choose?

Q4_K_M is the usual starting point for Kanana 1.5 15.7b A3B Instruct: it balances file size and quality well. Here it is a 10.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters15.7B (approximate, mixture of experts)
Active parameters3B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyKanana
Licenseother
Downloads (HF)687
Last updated2025-12-18

Frequently asked questions about Kanana 1.5 15.7b A3B Instruct

How much VRAM does Kanana 1.5 15.7b A3B Instruct need?

About 12.0 GB at Q4_K_M with an 8K context window. That is the 10.4 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 1.5 15.7b A3B Instruct on an 8 GB GPU?

Yes, with IQ2_M: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kanana 1.5 15.7b A3B Instruct GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 5.1 GB, IQ1_M is 5.3 GB, IQ2_XXS is 5.7 GB, IQ2_XS is 6.0 GB, IQ2_S is 6.1 GB and 19 more.

What context length does Kanana 1.5 15.7b 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Kanana 1.5 15.7b A3B Instruct GGUF?

The files are on Hugging Face in the mradermacher/kanana-1.5-15.7b-a3b-instruct-i1-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 1.5 15.7b 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 this model on 8 GB VRAM?

Use the Q4_K_M quantization; it requires about 12 GB memory at 8 k context, which is close to 8 GB but may need off‑load or lower batch size.

Does the model support vision?

No, the model has no vision capability.

What context length does it support?

It supports up to 32 768 tokens.

Other GGUFs of kanana-1.5-15.7b-a3b-instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kanana models

All Kanana →

Other medium models

All medium models →