AW

AWAXIS Think 28B

AwaxisGGUF by mradermacherUpdated 2026-04-26
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant0.0 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 24 quants, from 0.0 GB to 22.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

AWAXIS Think 28B – Korean‑focused 28B LLM with long‑context support

AWAXIS Think 28B is a 26.9B parameter model based on Qwen3.5. It inherits reasoning and tool use abilities and supports a 262144‑token context window. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Long‑context reasoning
  • Tool‑enabled inference
  • Korean language fluency

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Chatbots needing 262k token context
  • Research on Korean NLP
  • Tool‑integrated applications

Who it’s for. Developers building Korean‑centric chat or research systems that need extended context. The model is suitable for users with GPU memory to run higher‑quality quants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.1 GB 9.8 GB
Too big Get file →
IQ1_M7.6 GB 10.3 GB
Too big Get file →
IQ2_XXS8.4 GB 11.1 GB
Too big Get file →
IQ2_XS9.1 GB 11.7 GB
Too big Get file →
IQ2_S9.4 GB 12.0 GB
Too big Get file →
IQ2_M10.0 GB 12.7 GB
Too big Get file →
Q2_K_S10.2 GB 12.9 GB
Too big Get file →
Q2_K10.7 GB 13.4 GB
Too big Get file →
IQ3_XXS11.2 GB 13.8 GB
Too big Get file →
IQ3_XS12.0 GB 14.6 GB
Too big Get file →
Q3_K_S12.1 GB 14.7 GB
Too big Get file →
IQ3_S12.4 GB 15.1 GB
Too big Get file →
IQ3_M12.6 GB 15.2 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_XS15.1 GB 17.7 GB
Too big Get file →
Q4_015.5 GB 18.2 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 →
Q4_117.1 GB 19.7 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 →

For 8 GB VRAM, use IQ1_S (7.15 GB, 9.8 GB memory at 8k context) or IQ1_M (7.63 GB, 10.3 GB). For 12 GB VRAM, Q2_K (10.71 GB, 13.4 GB) or Q3_K_M (13.3 GB, 15.9 GB) are reasonable. Higher quants like Q4_K_M or Q5_K_M require 16–20 GB VRAM.

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: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (9.4 GB file, about 12.0 GB in use).
  • 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 Q6_K (22.1 GB file, about 24.7 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.

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

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

Source

Quantized bymradermacher
FamilyAwaxis
Licenseapache-2.0
Downloads (HF)536
Last updated2026-04-26

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?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.0 GB, IQ1_S is 7.1 GB, IQ1_M is 7.6 GB, IQ2_XXS is 8.4 GB, IQ2_XS is 9.1 GB, IQ2_S is 9.4 GB and 18 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-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 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 IQ1_S or IQ1_M quant; they fit within 8 GB VRAM with about 10 GB memory usage at 8k context.

Does the model support vision inputs?

No, the model is text‑only; no mmproj files are provided.

What context length does it support?

It supports up to 262,144 tokens, enabling very long‑context inference.

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 →