AW

AWAXIS Think 28B

AwaxisGGUF by mradermacherUpdated 2026-10-16
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant10.7 GB
Quick answer

AWAXIS Think 28B needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.7 GB (Q2_K) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

AWAXIS Think 28B – 26.9B parameter Korean‑focused LLM

AWAXIS Think 28B is a 26.9B parameter model built on Qwen3.5 architecture. It combines Darwin V7 evolutionary merging of Qwen3.6‑27B and Claude‑Opus distilled models, then applies a Korean LoRA. The model supports reasoning, tools, and vision.

Good at

  • Korean Q&A and conversation
  • Long‑form reasoning with chain‑of‑thought
  • Multilingual cross‑language tasks

Limits

  • No vision support in GGUF files
  • Requires large VRAM for full precision
  • Apache‑2.0 license requires base model attribution

Best for

  • Korean content generation
  • Multilingual translation and summarization
  • Long‑context analysis

Who it’s for. Developers and researchers needing a Korean‑optimized LLM with strong reasoning and tool‑use capabilities. Suitable for applications that can run on GPUs with sufficient VRAM and comply with Apache‑2.0 licensing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.7 GB 13.4 GB
Too big Get file →
Q3_K_S12.1 GB 14.7 GB
Too big Get file →
Q3_K_M13.3 GB 15.9 GB
Too big Get file →
Q3_K_L14.3 GB 17.0 GB
Too big Get file →
IQ4_XS15.2 GB 17.8 GB
Too big Get file →
Q4_K_S15.6 GB 18.2 GB
Too big Get file →
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q5_K_S18.7 GB 21.3 GB
Too big Get file →
Q5_K_M19.2 GB 21.9 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (10.71 GB file, 13.4 GB memory). For 12 GB VRAM, Q3_K_S (12.07 GB file, 14.7 GB memory). For 16 GB VRAM, Q4_K_M (16.55 GB file, 19.2 GB memory). Memory estimates are approximate.

What GPU do you need for AWAXIS Think 28B?

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: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which AWAXIS Think 28B quant should you choose?

Q4_K_M is the usual starting point for AWAXIS Think 28B: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 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 Q2_K at 10.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyAwaxis
Licenseapache-2.0
Downloads (HF)781
Last updated2026-10-16

Frequently asked questions about AWAXIS Think 28B

How much VRAM does AWAXIS Think 28B need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 AWAXIS Think 28B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AWAXIS Think 28B GGUF?

It depends on the quant: Q2_K is 10.7 GB, Q3_K_S is 12.1 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.2 GB, Q4_K_S is 15.6 GB and 5 more.

What context length does AWAXIS Think 28B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download AWAXIS Think 28B GGUF?

The files are on Hugging Face in the mradermacher/AWAXIS-Think-28B-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 AWAXIS Think 28B 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 AWAXIS Think 28B on 8 GB VRAM?

Use the Q2_K quant, which requires about 13.4 GB of VRAM at 8k context. It may fit with lower context or batch size.

Does the model support vision tasks?

The provided GGUF files do not include vision support. Vision capabilities are not available in this release.

What license applies to this model?

The model is licensed under Apache‑2.0. Commercial and academic use is allowed with attribution of the base model.

Other GGUFs of AWAXIS-Think-28B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Awaxis models

All Awaxis →

Other medium models

All medium models →