QW

Qwen3.5 9B gemini 3.1 opus 4.6 reasoning

QwenGGUF by Momix-44Updated 2026-03-31
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant3.1 GB
Quick answer

Qwen3.5 9B gemini 3.1 opus 4.6 reasoning needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 3.1 GB (IQ2_XXS) to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Qwen3.5 9B gemini 3.1 opus 4.6 reasoning – a 9B causal language model focused on reasoning and vision

Qwen3.5 9B gemini 3.1 opus 4.6 reasoning is a 9B‑scale causal language model based on Qwen/Qwen3.5-9B. It is optimized for structured reasoning, multiple‑choice QA, and general zero‑shot evaluation. The model supports vision, reasoning, and tools.

Good at

  • Structured reasoning
  • Multiple‑choice QA
  • Vision tasks

Limits

  • No dedicated vision support in llama.cpp
  • Large VRAM requirement for higher context
  • License is apache‑2.0

Best for

  • Zero‑shot reasoning tasks
  • Multi‑modal inference with vision
  • Agent‑style tool usage

Who it’s for. Developers needing a reasoning‑oriented LLM with vision capability. The model is suitable for applications that require accurate multiple‑choice answers and structured reasoning in a multimodal setting.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS3.1 GB 4.7 GB
Fits Get file →
IQ2_XS3.3 GB 4.9 GB
Fits Get file →
IQ2_M3.6 GB 5.2 GB
Fits Get file →
IQ3_XS4.2 GB 5.8 GB
Fits Get file →
Q3_K_S4.3 GB 5.8 GB
Fits Get file →
Q3_K_M4.6 GB 6.2 GB
Fits Get file →
IQ4_XS5.2 GB 6.8 GB
Fits Get file →
IQ4_NL5.4 GB 7.0 GB
Fits Get file →
Q4_K_M5.6 GB 7.2 GB
Tight Get file →
Q5_K_M6.5 GB 8.0 GB
Too big Get file →
Q6_K7.4 GB 8.9 GB
Too big Get file →
MXFP49.5 GB 11.1 GB
Too big Get file →
Q8_09.5 GB 11.1 GB
Too big Get file →
BF1617.9 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, the Q4_K_M quant (file size 5.63 GB, estimated 7.2 GB at 8k context) is a good balance. If more memory is available, Q5_K_M (6.47 GB, 8 GB) or Q6_K (7.36 GB, 8.9 GB) provide higher precision. Smaller quants like IQ2_XS (3.29 GB, 4.9 GB) fit tighter budgets but reduce accuracy.

What GPU do you need for Qwen3.5 9B gemini 3.1 opus 4.6 reasoning?

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: the best quant that fits is Q3_K_S (4.3 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).

Which Qwen3.5 9B gemini 3.1 opus 4.6 reasoning quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 9B gemini 3.1 opus 4.6 reasoning: it balances file size and quality well. Here it is a 5.6 GB file.

The Q8_0 file is 9.5 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 IQ2_XXS at 3.1 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
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMomix-44
FamilyQwen
Base modelQwen/Qwen3.5-9B
Licenseapache-2.0
Downloads (HF)677
Last updated2026-03-31

Frequently asked questions about Qwen3.5 9B gemini 3.1 opus 4.6 reasoning

How much VRAM does Qwen3.5 9B gemini 3.1 opus 4.6 reasoning need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 9B gemini 3.1 opus 4.6 reasoning on an 8 GB GPU?

Yes, with Q5_K_M: the 6.5 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 Qwen3.5 9B gemini 3.1 opus 4.6 reasoning GGUF?

It depends on the quant: IQ2_XXS is 3.1 GB, IQ2_XS is 3.3 GB, IQ2_M is 3.6 GB, IQ3_XS is 4.2 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.6 GB and 8 more.

What context length does Qwen3.5 9B gemini 3.1 opus 4.6 reasoning support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Qwen3.5 9B gemini 3.1 opus 4.6 reasoning GGUF?

The files are on Hugging Face in the Momix-44/Qwen3.5-9B-gemini-3.1-opus-4.6-reasoning 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 9B gemini 3.1 opus 4.6 reasoning 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 Qwen3.5 9B gemini 3.1 opus 4.6 reasoning on 8 GB VRAM?

Yes, the Q4_K_M quant uses approximately 7.2 GB at 8k context, fitting within an 8 GB VRAM budget.

Does this model support vision tasks in llama.cpp?

The model has detected vision ability, but llama.cpp does not provide dedicated vision support for this quant.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3.5-9B

Similar models

Browse all →

More from Momix-44

All by Momix-44 →

More Qwen models

All Qwen →

Other small models

All small models →