QW

qwen3.5 4B super coder

QwenGGUF by thunquantUpdated 2026-08-19
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant2.6 GB
Quick answer

qwen3.5 4B super coder needs about 4.2 GB of memory at Q4_0 (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Qwen3.5‑4B Super Coder – 4‑bit GGUF model for coding, reasoning, tools and vision

Qwen3.5‑4B Super Coder is a 4‑bit quantized GGUF model optimized for mobile and consumer hardware. It supports coding, reasoning, structured tool calling and vision tasks. The model is distilled from Claude Sonnet 4.6 and Opus 4.6 and uses a hybrid Gated DeltaNet and full attention architecture.

Good at

  • Coding accuracy across Python, JS, Shell
  • Structured tool calling
  • Vision‑language reasoning

Limits

  • No license information provided
  • Context length limited to 262144 tokens
  • No explicit support for large‑scale multimodal training

Best for

  • Mobile coding assistants
  • Tool‑enabled code generation
  • Vision‑augmented code review

Who it’s for. Developers and hobbyists needing a lightweight, fast model for coding and tool integration on mobile or edge devices. The model is suitable for users who want structured tool calls and basic vision support without heavy GPU resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.6 GB 4.2 GB
Fits Get file →

The Q4_0 quantization produces a 2.61 GB file and requires approximately 4.2 GB of VRAM at 8 k context. This is suitable for systems with 8 GB or more VRAM. For tighter budgets, consider a lower‑bit quant if available, but it is not listed in the file set.

What GPU do you need for qwen3.5 4B super 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: the best quant that fits is Q4_0 (2.6 GB file, about 4.2 GB in use).

Which qwen3.5 4B super coder quant should you choose?

Q4_0 (2.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.33B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bythunquant
FamilyQwen
Base modelQwen/Qwen3.5-4B
Downloads (HF)1,030
Last updated2026-08-19

Frequently asked questions about qwen3.5 4B super coder

How much VRAM does qwen3.5 4B super coder need?

About 4.2 GB at Q4_0 with an 8K context window. That is the 2.6 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 4B super coder on an 8 GB GPU?

Yes, with Q4_0: the 2.6 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of qwen3.5 4B super coder GGUF?

It depends on the quant: Q4_0 is 2.6 GB.

What context length does qwen3.5 4B super 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 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download qwen3.5 4B super coder GGUF?

The files are on Hugging Face in the thunquant/qwen3.5-4B-super-coder repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q4_0 quant requires about 4.2 GB of VRAM at 8 k context, fitting comfortably on an 8 GB GPU.

Does the model support vision tasks?

Yes, the model includes a vision encoder and supports vision‑language tasks.

What is the maximum context length?

The model supports up to 262144 tokens, with native support for larger contexts via YaRN.

Other GGUFs of Qwen3.5-4B

Similar models

Browse all →

More from thunquant

All by thunquant →

More Qwen models

All Qwen →

Other small models

All small models →