NA

Napoleon 3.5 12B

NapoleonGGUF by mradermacherUpdated 2026-10-13
Download on Hugging Face
Parameters10.7B
Context256K
Layers40
Architectureqwen35
Smallest quant4.5 GB
Quick answer

Napoleon 3.5 12B needs about 8.5 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 4.5 GB (Q2_K) to 21.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Napoleon 3.5 12B – a 12B Qwen3.5‑based model with multimodal vision

Napoleon 3.5 12B is a 12B parameter model built by expanding Qwen3.5‑9B from 32 to 40 layers. It retains full vision encoder support and is released under Apache‑2.0. The model is available in 12 static quantizations.

Good at

  • reasoning
  • tools
  • vision

Limits

  • trained context 262144 tokens
  • no additional vision encoder beyond base
  • Apache‑2.0 license

Best for

  • multimodal chat
  • image‑guided reasoning
  • tool‑enabled tasks

Who it’s for. Developers and researchers who need a 12B model with vision capabilities and a permissive license. The model is suitable for local deployment via llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.5 GB 6.3 GB
Fits Get file →
Q3_K_S5.0 GB 6.8 GB
Fits Get file →
Q3_K_M5.5 GB 7.3 GB
Tight Get file →
Q3_K_L5.8 GB 7.7 GB
Tight Get file →
IQ4_XS6.2 GB 8.0 GB
Too big Get file →
Q4_K_S6.3 GB 8.2 GB
Too big Get file →
Q4_K_M6.7 GB 8.5 GB
Too big Get file →
Q5_K_S7.5 GB 9.3 GB
Too big Get file →
Q5_K_M7.7 GB 9.5 GB
Too big Get file →
Q6_K8.8 GB 10.6 GB
Too big Get file →
Q8_011.4 GB 13.2 GB
Too big Get file →
F1621.4 GB 23.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (6.67 GB file, ~8.5 GB memory). For 12 GB VRAM, Q5_K_M (7.69 GB file, ~9.5 GB memory) or Q6_K (8.78 GB file, ~10.6 GB memory). Higher‑precision quants require more memory.

What GPU do you need for Napoleon 3.5 12B?

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: the best quant that fits is IQ4_XS (6.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (21.4 GB file, about 23.2 GB in use).

Which Napoleon 3.5 12B quant should you choose?

Q4_K_M is the usual starting point for Napoleon 3.5 12B: it balances file size and quality well. Here it is a 6.7 GB file.

The Q8_0 file is 11.4 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 4.5 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
Parameters10.7B
Layers40
Trained context262,144 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyNapoleon
Licenseapache-2.0
Downloads (HF)750
Last updated2026-10-13

Frequently asked questions about Napoleon 3.5 12B

How much VRAM does Napoleon 3.5 12B need?

About 8.5 GB at Q4_K_M with an 8K context window. That is the 6.7 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 Napoleon 3.5 12B on an 8 GB GPU?

Yes, with IQ4_XS: the 6.2 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 Napoleon 3.5 12B GGUF?

It depends on the quant: Q2_K is 4.5 GB, Q3_K_S is 5.0 GB, Q3_K_M is 5.5 GB, Q3_K_L is 5.8 GB, IQ4_XS is 6.2 GB, Q4_K_S is 6.3 GB and 6 more.

What context length does Napoleon 3.5 12B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Napoleon 3.5 12B GGUF?

The files are on Hugging Face in the mradermacher/Napoleon-3.5-12B-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 Napoleon 3.5 12B 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 Q4_K_M on 8 GB VRAM?

Yes, Q4_K_M uses 6.67 GB file and estimates 8.5 GB memory at 8k context, which fits 8 GB VRAM with some overhead.

Does the model support image input?

Yes, the vision encoder is unchanged, so image and video inputs are fully supported.

What license applies to this model?

The model is released under Apache‑2.0, allowing commercial and non‑commercial use.

Other GGUFs of Napoleon-3.5-12B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Napoleon models

All Napoleon →

Other medium models

All medium models →