QW

Qwen 35B A3B SignOfFour Coder

QwenGGUF by pragmaticcsUpdated 2026-10-27
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant21.5 GB
Quick answer

Qwen 35B A3B SignOfFour Coder needs about 22.6 GB of memory at Q4_K_M (a 21.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 21.5 GB (Q4_K_M) to 69.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen 35B A3B SignOfFour Coder – a 35B MoE coding‑agent model

Qwen 35B A3B SignOfFour Coder is a 35B‑parameter, 3B‑active‑parameter mixture‑of‑experts model fine‑tuned for coding workflows. It is optimized for short, token‑efficient reasoning and tool‑based code editing. The model is released under Apache‑2.0 and is intended for local agentic coding evaluation.

Good at

  • Token‑efficient coding
  • Tool‑based code editing
  • Agentic workflow execution

Limits

  • Large VRAM requirement – 22–38 GB at 8 k context
  • No vision support
  • Experimental release – no safety evaluation

Best for

  • Local coding‑agent prototyping
  • Tool‑calling code generation
  • Debug‑driven code editing

Who it’s for. Developers and researchers who need a local, high‑throughput coding agent. The model is suitable for evaluating agent harnesses and experimenting with coding workflows, but it is not a production‑ready solution.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M21.5 GB 22.6 GB
Too big Get file →
Q5_K_M25.0 GB 26.1 GB
Too big Get file →
—25.1 GB 26.3 GB
Too big Get file →
Q6_K28.7 GB 29.8 GB
Too big Get file →
Q8_036.9 GB 38.1 GB
Too big Get file →
BF1669.4 GB (2 parts) 70.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (21.48 GB file, ~22.6 GB memory). With 12 GB VRAM Q5_K_M (24.96 GB file, ~26.1 GB memory). For 16 GB VRAM Q6_K (28.67 GB file, ~29.8 GB memory).

What GPU do you need for Qwen 35B A3B SignOfFour Coder?

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 (21.5 GB file, about 22.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.7 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.9 GB file, about 38.1 GB in use).

Which Qwen 35B A3B SignOfFour Coder quant should you choose?

Q4_K_M is the usual starting point for Qwen 35B A3B SignOfFour Coder: it balances file size and quality well. Here it is a 21.5 GB file.

The Q8_0 file is 36.9 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

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

Source

Quantized bypragmaticcs
FamilyQwen
Licenseapache-2.0
Downloads (HF)7,784
Last updated2026-10-27

Frequently asked questions about Qwen 35B A3B SignOfFour Coder

How much VRAM does Qwen 35B A3B SignOfFour Coder need?

About 22.6 GB at Q4_K_M with an 8K context window. That is the 21.5 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 Qwen 35B A3B SignOfFour Coder on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen 35B A3B SignOfFour Coder GGUF?

It depends on the quant: Q4_K_M is 21.5 GB, Q5_K_M is 25.0 GB, file is 25.1 GB, Q6_K is 28.7 GB, Q8_0 is 36.9 GB, BF16 is 69.4 GB.

What context length does Qwen 35B A3B SignOfFour Coder 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 Qwen 35B A3B SignOfFour Coder GGUF?

The files are on Hugging Face in the pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-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 Qwen 35B A3B SignOfFour Coder 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 Qwen 35B A3B SignOfFour Coder on 8 GB VRAM?

No. The smallest quant requires ~22.6 GB VRAM at 8 k context. 8 GB VRAM is insufficient.

Does the model support image input?

No. Vision weights have been removed to reduce VRAM footprint.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwopus3.6-35B-A3B-Coder

Similar models

Browse all →

More from pragmaticcs

All by pragmaticcs →

More Qwen models

All Qwen →

Other large models

All large models →