QW

STEM Oracle

QwenGGUF by VerdugieUpdated 2026-10-26
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant16.5 GB
Quick answer

STEM Oracle 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 4 quants, from 16.5 GB (Q4_K_M) to 53.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

STEM Oracle – a Qwen3.5‑27B fine‑tuned for STEM reasoning

STEM Oracle is a 26.9‑billion‑parameter model fine‑tuned from Qwen3.5‑27B on 5,179 STEM conversations. It specializes in introductory math, physics, chemistry, biology, and computer science reasoning. The model is released under the apache‑2.0 license.

Good at

  • STEM reasoning
  • plain‑sentence explanations
  • few‑turn Q&A

Limits

  • No vision support
  • trained context 262,144 tokens
  • requires large VRAM for higher precision

Best for

  • Educational tutoring
  • Homework help
  • Concept explanations

Who it’s for. Developers building educational tools or students needing concise STEM explanations. The model is ideal for applications that require clear, short answers to technical questions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.5 GB 19.2 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 →
BF1653.8 GB 56.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (16.55 GB file, ~19.2 GB memory at 8 k context). For 12 GB VRAM use Q6_K (22.08 GB file, ~24.7 GB memory). For 16 GB VRAM use Q8_0 (28.59 GB file, ~31.2 GB memory). BF16 requires ~56.5 GB memory and is not recommended for limited VRAM.

What GPU do you need for STEM Oracle?

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 (16.5 GB file, about 19.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which STEM Oracle quant should you choose?

Q4_K_M is the usual starting point for STEM Oracle: 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.

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 byVerdugie
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,814
Last updated2026-10-26

Frequently asked questions about STEM Oracle

How much VRAM does STEM Oracle 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 STEM Oracle on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of STEM Oracle GGUF?

It depends on the quant: Q4_K_M is 16.5 GB, Q6_K is 22.1 GB, Q8_0 is 28.6 GB, BF16 is 53.8 GB.

What context length does STEM Oracle 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 STEM Oracle GGUF?

The files are on Hugging Face in the Verdugie/STEM-Oracle repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does STEM Oracle 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 STEM Oracle on 8 GB VRAM?

Use the Q4_K_M quantized file; it requires about 19.2 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does STEM Oracle support image inputs?

No, the model has no vision capabilities.

What license applies to STEM Oracle?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3.5-27B

Similar models

Browse all →

More from Verdugie

All by Verdugie →

More Qwen models

All Qwen →

Other medium models

All medium models →