QW

Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking

QwenGGUF by mradermacherUpdated 2026-03-04
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking 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.

Qwen3.5 27B Gemini3 Pro – compact reasoning model

Qwen3.5 27B Gemini3 Pro is a 26.9B‑parameter model fine‑tuned with Gemini distill data. It supports reasoning, roleplay, and tool use. The model is released under apache‑2.0 and is in early alpha.

Good at

  • Reasoning
  • Roleplay
  • Tool integration

Limits

  • Alpha release, may loop in think block
  • No safety alignment changes yet
  • Vision support not fully tested

Best for

  • Complex reasoning tasks
  • Interactive roleplay scenarios
  • Automated tool workflows

Who it’s for. Developers needing a compact, reasoning‑focused LLM for local deployment. Suitable for research and prototyping where safety alignment is not critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S6.2 GB 8.9 GB
Too big Get file →
IQ1_M6.8 GB 9.4 GB
Too big Get file →
IQ2_XXS7.7 GB 10.3 GB
Too big Get file →
IQ2_XS8.4 GB 11.0 GB
Too big Get file →
IQ2_S8.7 GB 11.3 GB
Too big Get file →
IQ2_M9.4 GB 12.0 GB
Too big Get file →
Q2_K_S9.7 GB 12.3 GB
Too big Get file →
Q2_K10.1 GB 12.8 GB
Too big Get file →
IQ3_XXS10.7 GB 13.4 GB
Too big Get file →
IQ3_XS11.6 GB 14.3 GB
Too big Get file →
Q3_K_S12.1 GB 14.7 GB
Too big Get file →
IQ3_S12.1 GB 14.7 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_L14.0 GB 16.7 GB
Too big Get file →
IQ4_XS14.7 GB 17.3 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_M19.4 GB 22.0 GB
Too big Get file →
Q6_K22.1 GB 24.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.23 GB, 8.9 GB memory at 8 k context). For 12 GB VRAM, IQ2_M (9.4 GB, 12 GB memory). For 24 GB VRAM, Q6_K (22.08 GB, 24.7 GB memory). Estimates are approximate.

What GPU do you need for Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking?

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_M (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 (19.4 GB file, about 22.0 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 Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking: 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

Frequently asked questions about Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking

How much VRAM does Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking 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 Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking 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 Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 6.2 GB, IQ1_M is 6.8 GB, IQ2_XXS is 7.7 GB, IQ2_XS is 8.4 GB, IQ2_S is 8.7 GB and 18 more.

What context length does Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking 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 Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking GGUF?

The files are on Hugging Face in the mradermacher/Qwen3.5-27B-Gemini3-Pro-High-Reasoning-Compact-Thinking-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 Qwen3.5 27B Gemini3 Pro High Reasoning Compact Thinking 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant is 6.23 GB and requires about 8.9 GB memory at 8 k context.

Does this model have safety alignment?

No safety alignment changes were made; the model is in early alpha.

Is vision support available?

Vision is tested but not fully validated; mmproj files may be available in the static repo.

Other GGUFs of Qwen3.5-27B-Gemini3-Pro-High-Reasoning-Compact-Thinking

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →