You can deploy this model and start earning money today!

bigatuna/
Qwen3.5-27b-Sushi-Coder-RL-GGUF

Name: Qwen3.5-27b-Sushi-Coder-RL-GGUF
Availability: InStock

Views

No views yet

Qwen3.5-27b-Sushi-Coder-RL-GGUF

This is the 27B GGUF release in the Sushi Coder RL line.

It is the bigger sibling to bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF, built with the same overall recipe but at 27B scale.

Training followed this sequence:

Start from the Unsloth 16-bit Qwen 3.5 27B base: unsloth/Qwen3.5-27B
SFT on open-r1/codeforces-cots using Unsloth
Run RL on top with a custom coding environment built using NousResearch/atropos, OpenAI Codex, and NousResearch/hermes-agent

Download the Q4 quant:

bash

hf download bigatuna/Qwen3.5-27b-Sushi-Coder-RL-GGUF \
  qwen35-codeforces-27b-rl-step25-Q4_K_M.gguf

Download the Q8 quant:

bash

hf download bigatuna/Qwen3.5-27b-Sushi-Coder-RL-GGUF \
  qwen35-codeforces-27b-rl-step25-Q8_0.gguf

There are no 27B evals posted yet.

Evals are expensive and take time, and the current plan is to post them in the next few weeks.

If you want a reference point in the meantime, you can look at the evals on the 9B sibling repo:

Open to sponsorship if you want to help fund evals and future releases.

This repo currently contains GGUF exports only.