QW

Qwen3.5 27b Sushi Coder RL

QwenGGUF by bigatunaUpdated 2026-04-03
Download on Hugging Face
Parameters27B
Context256K
Layers64
Architectureqwen35
Smallest quant16.5 GB
Quick answer

Qwen3.5 27b Sushi Coder RL needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 16.5 GB (Q4_K_M) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

27B Qwen3.5 Sushi Coder RL for coding and reasoning

Qwen3.5 27b Sushi Coder RL is a 27B causal language model with a focus on coding, reasoning, and tool use. It is released in GGUF format and can be run with llama.cpp or compatible frameworks. The model is trained on a 262144 token context and licensed under Apache‑2.0.

Good at

  • Coding tasks
  • Logical reasoning
  • Tool integration

Limits

  • Requires >19.2GB VRAM for Q4_K_M
  • No evaluation results available yet
  • Large model size

Best for

  • Automated code generation
  • Debugging assistance
  • Tool‑driven workflows

Who it’s for. Developers and researchers who need a large‑scale model for coding assistance and reasoning tasks. The model is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.5 GB 19.2 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →

For 8‑12GB VRAM, use the Q4_K_M quant (file size 16.55GB, estimated memory 19.2GB). For 16‑20GB VRAM, the Q8_0 quant (28.6GB, 31.2GB) provides higher precision. Memory estimates are approximate.

What GPU do you need for Qwen3.5 27b Sushi Coder RL?

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 (16.5 GB file, about 19.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).

Which Qwen3.5 27b Sushi Coder RL quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 27b Sushi Coder RL: it balances file size and quality well. Here it is a 16.5 GB file.

The Q8_0 file is 28.6 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

Architectureqwen35
Parameters27B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bybigatuna
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,848
Last updated2026-04-03

Frequently asked questions about Qwen3.5 27b Sushi Coder RL

How much VRAM does Qwen3.5 27b Sushi Coder RL need?

About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Qwen3.5 27b Sushi Coder RL on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5 27b Sushi Coder RL GGUF?

It depends on the quant: Q4_K_M is 16.5 GB, Q8_0 is 28.6 GB.

What context length does Qwen3.5 27b Sushi Coder RL support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Qwen3.5 27b Sushi Coder RL GGUF?

The files are on Hugging Face in the bigatuna/Qwen3.5-27b-Sushi-Coder-RL-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 Qwen3.5 27b Sushi Coder RL 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 this model on 8GB VRAM?

No, the smallest quant requires at least 19.2GB of VRAM at 8k context.

Does the model support vision inputs?

The model is described as a vision‑language foundation, but no explicit vision support is listed in the provided facts.

Is the model open source?

Yes, it is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-27B

Similar models

Browse all →

More from bigatuna

All by bigatuna →

More Qwen models

All Qwen →

Other medium models

All medium models →