DA

Darwin 35B A3B Opus

DarwinGGUF by mradermacherUpdated 2026-04-21
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant0.2 GB
Quick answer

Darwin 35B A3B Opus needs about 22.3 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.2 GB to 28.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Darwin 35B A3B Opus – a 35B MoE vision model with 262K context

Darwin 35B A3B Opus is a 35B parameter mixture‑of‑experts model based on Qwen3.5‑35B‑A3B. It supports reasoning, tools, and vision. The model is released under Apache‑2.0 and can run on iPhone or CPU without a GPU.

Good at

  • Reasoning and logic tasks
  • Multimodal vision input
  • Tool‑use integration

Limits

  • Large VRAM requirement for full precision
  • No dedicated vision file included in this listing
  • Requires llama.cpp for execution

Best for

  • Complex reasoning workflows
  • Vision‑enabled chat applications
  • Tool‑augmented LLM use cases

Who it’s for. Developers building multimodal applications who need a large‑scale MoE model with reasoning and tool support. The model is suitable for environments with sufficient GPU memory or CPU‑only setups using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.2 GB 1.4 GB
Fits Get file →
IQ1_S7.5 GB 8.7 GB
Too big Get file →
IQ1_M8.2 GB 9.4 GB
Too big Get file →
IQ2_XXS9.5 GB 10.7 GB
Too big Get file →
IQ2_XS10.5 GB 11.7 GB
Too big Get file →
IQ2_S10.7 GB 11.8 GB
Too big Get file →
IQ2_M11.7 GB 12.8 GB
Too big Get file →
Q2_K_S12.2 GB 13.3 GB
Too big Get file →
Q2_K12.9 GB 14.1 GB
Too big Get file →
IQ3_XXS13.6 GB 14.8 GB
Too big Get file →
IQ3_XS14.5 GB 15.7 GB
Too big Get file →
Q3_K_S15.2 GB 16.4 GB
Too big Get file →
IQ3_S15.3 GB 16.4 GB
Too big Get file →
IQ3_M15.4 GB 16.6 GB
Too big Get file →
Q3_K_M16.8 GB 17.9 GB
Too big Get file →
Q3_K_L18.1 GB 19.3 GB
Too big Get file →
IQ4_XS18.7 GB 19.9 GB
Too big Get file →
Q4_019.8 GB 21.0 GB
Too big Get file →
Q4_K_S19.9 GB 21.1 GB
Too big Get file →
Q4_K_M21.2 GB 22.3 GB
Too big Get file →
Q4_121.8 GB 23.0 GB
Too big Get file →
Q5_K_S24.0 GB 25.2 GB
Too big Get file →
Q5_K_M24.7 GB 25.9 GB
Too big Get file →
Q6_K28.5 GB 29.7 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.48 GB, 8.7 GB memory at 8 k context). For 12 GB VRAM, IQ2_XS (10.51 GB, 11.7 GB memory) or Q2_K (12.94 GB, 14.1 GB memory). For 16 GB VRAM, Q3_K_M (16.76 GB, 17.9 GB memory) or Q4_K_S (19.89 GB, 21.1 GB memory). Estimates are approximate.

What GPU do you need for Darwin 35B A3B Opus?

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 (0.2 GB file, about 1.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.2 GB file, about 1.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_S (10.7 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (14.5 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (21.8 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.5 GB file, about 29.7 GB in use).

Which Darwin 35B A3B Opus quant should you choose?

Q4_K_M is the usual starting point for Darwin 35B A3B Opus: it balances file size and quality well. Here it is a 21.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.2 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

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymradermacher
FamilyDarwin
Licenseapache-2.0
Downloads (HF)1,078
Last updated2026-04-21

Frequently asked questions about Darwin 35B A3B Opus

How much VRAM does Darwin 35B A3B Opus need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 Darwin 35B A3B Opus on an 8 GB GPU?

Yes, with the smaller files: the 0.2 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Darwin 35B A3B Opus GGUF?

It depends on the quant: file is 0.2 GB, IQ1_S is 7.5 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.5 GB, IQ2_XS is 10.5 GB, IQ2_S is 10.7 GB and 18 more.

What context length does Darwin 35B A3B Opus support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Darwin 35B A3B Opus GGUF?

The files are on Hugging Face in the mradermacher/Darwin-35B-A3B-Opus-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 Darwin 35B A3B Opus 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 Darwin 35B A3B Opus on 8 GB VRAM?

Use the IQ1_S quant which is 7.48 GB and requires about 8.7 GB memory at 8 k context.

Does the model support vision on CPU?

Yes, the model is a vision model and can run on CPU via llama.cpp, but performance will be slower.

What license applies to this model?

The model is released under Apache‑2.0.

Other GGUFs of Darwin-35B-A3B-Opus

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Darwin models

All Darwin →

Other large models

All large models →