GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
moxin-org
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
moxin-org
Model Tree
Qwen/Qwen3.5-27B
Input Modalities
Output Modalities
Supported Functionality
Pu Zhao, Changdi Yang, Yixiao Chen, Yi Gao, Yifan Cao, Haochen Zeng, and Yanzhi Wang. Northeastern University · EmbodyX Inc · Aibao LLC
The arXiv title uses “Qwen3-27B”; Section 3 identifies the released source checkpoint as
Qwen/Qwen3.5-27B, which is the identifier used throughout this model card.
87.30% execution-verified C2Rust Success Rate — a 15.00 percentage-point gain over the untuned Qwen3.5-27B base at identical model size. The 27B checkpoint also outperforms Qwen3.5-Plus (397B total), MiniMax-M2.5 (230B total), and GLM-5 (744B total) on this benchmark.
Success Rate (SR) is the percentage of programs that compile and pass every end-to-end test. Scores are arithmetic means over five random seeds under the same inference configuration.
| Model | Model size | SR |
|---|---|---|
| Qwen3.5-Plus | 397B total / 17B active | 77.20% |
| MiniMax-M2.5 | 230B total / 10B active | 83.90% |
| GLM-5 | 744B total / 40B active | 84.40% |
| GLM-5.2 | 744B total / 40B active | 89.90% |
| Claude Code-4.6 | undisclosed | 90.01% |
| Qwen3.5-27B base | 27B dense | 72.30% |
| C2Rust (this model) | 27B dense | 87.30% |
The curriculum improves the direct Qwen3.5-27B baseline by 15.00 percentage points while keeping model size and serving cost fixed. C2Rust outperforms Qwen3.5-Plus, MiniMax-M2.5, and GLM-5 on this task, while remaining below GLM-5.2 and Claude Code-4.6.
| Model | SWE-bench Verified pass@1 |
|---|---|
| GPT-5-mini (2025-08-07) | 72.0 |
| GPT-OSS-120B | 62.0 |
| Qwen3.5-122B-A10B | 72.0 |
| Qwen3.5-27B base | 72.4 |
| C2Rust (this model) | 70.6 |
The 1.8-point difference from the untuned base suggests a modest specialization cost, while the model retains strong general software-engineering performance.
| Stage | Objective | Data | Training configuration |
|---|---|---|---|
| 1. Rust continued pretraining | Strengthen Rust syntax, idioms, completion, repair, and library knowledge | 1,673,289 examples from seven Rust-focused sources | Full-parameter BF16, 1 epoch, LR 1e-6 |
| 2. Debugging-aware SFT | Learn to consume structured verifier feedback and make targeted repairs | microsoft/Verus_Training_Data | Full-parameter BF16, 2 epochs, LR 2e-7 |
| 3. C2Rust task SFT |
Stage 1 combines Strandset-Rust, CodeFIM-Rust-Mellum, rust_instruction_dataset, humaneval-rust, the Rust subset of Magicoder-OSS-Instruct-75K, the Rust program-synthesis and repair subsets of xCodeEval, and the Rust subset of StarCoderData.
All three stages use a 16,384-token sequence length, DeepSpeed ZeRO Stage 3, and eight NVIDIA B300 GPUs. Training is text-only. The Qwen3.5 vision encoder remains in the released checkpoint but receives no task input and plays no role in C-to-Rust translation.
| Field | Value |
|---|---|
| Base model | Qwen/Qwen3.5-27B |
| Parameters | 27B language model (~28B including the retained vision encoder) |
| Weight format | Safetensors |
| Precision | BF16 |
| Context used in training | 16,384 tokens |
| Fine-tuning type | Full-parameter |
| Primary task | C-to-Rust program translation |
| License | Apache-2.0 |
The tokenizer, vocabulary, and architecture are unchanged from the base checkpoint; no task-specific special tokens were added.
The companion benchmark contains 200 C programs: 92 receive command-line arguments and 108 read standard input. Approximately 120 are derived from IBM Project CodeNet. A translation succeeds only when the generated Rust program compiles and reproduces every reference output on the supplied tests within a six-attempt translation and repair budget.
| Setting | Value |
|---|---|
| Temperature | 0.6 |
| Top-p | 0.95 |
| Top-k | 20 |
| Maximum output length | 1,536 tokens |
| Maximum translation attempts | 6 |
| Random seeds | 5 |
The released repository's default configs evaluate SACTOR's interface-preserving, unidiomatic stage.
Generated code may therefore contain raw pointers or unsafe Rust. Passing the benchmark measures
agreement on the supplied test suite, not formal semantic equivalence.
Download the checkpoint:
bash
hf download moxin-org/C2Rust --local-dir /path/to/C2Rust-model
Clone and prepare the benchmark:
bash
git clone https://github.com/moxin-org/C2Rust.gitcd C2Rustbash fix_paths.shcd engineuv sync./update_rust_ast_parser.shcargo build --releasecd ..
Launch the checkpoint with SGLang:
bash
export SERVE_VENV=/path/to/sglang-venv./scripts/launch_model.sh /path/to/C2Rust-model 0,1 30878 2
Run a two-program smoke test before the complete evaluation:
bash
python3 scripts/run_eval.py configs/native_prompt.toml results/_smoke \--modes argv --limit 2 --workers 1
See the benchmark README and
SETUP.md for the complete environment,
five-seed evaluation, aggregation, and troubleshooting workflow.
This release is intended for research and experimentation on C-to-Rust translation. Treat every generated program as a candidate: compile it, test it against the original implementation, and review it for correctness, safety, and maintainability before use.
unsafe Rust and prioritizes behavior preservation over idiomaticity.bibtex
@article{zhao2026c2rust,title = {Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT},author = {Zhao, Pu and Yang, Changdi and Chen, Yixiao and Gao, Yi and Cao, Yifan and Zeng, Haochen and Wang, Yanzhi},journal = {arXiv preprint arXiv:2608.13681},year = {2026},doi = {10.48550/arXiv.2608.13681}}
The checkpoint is released under Apache-2.0 and is derived from Qwen/Qwen3.5-27B. The benchmark is Apache-2.0. Its dataset includes material derived from IBM Project CodeNet under CDLA-Permissive-2.0; see the dataset provenance and terms.
| Learn direct C-to-Rust semantic translation |
C2Rust-Moxin functions/ and programs/ pairs |
Full-parameter BF16, 2 epochs, LR 2e-7 |