GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Taimwe
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Taimwe
Model Tree
unsloth/Qwen3-Coder-30B-A3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
v3 was retrained after v1 and v2 were found to emit the literal two-character sequence
\n instead of real newlines, which made their Python fail ast.parse. The cause was
JSON-escaped message text in parts of the training mix; it is fixed in
Taimwe/securecoder-scripts.
Same prompts, same harness (eval_securecoder.py):
| Model | Valid Python (15 prompts) | Tool calls: parse / name / schema (80 prompts) |
|---|---|---|
base unsloth/Qwen3-Coder-30B-A3B-Instruct | 93.3% | 100% / 100% / 100% |
securecoder-30b-pro-v2 | 0.0% | 100% / 100% / 100% |
| v3 (this model) | 100% | 100% / 100% / 100% |
Reports: base · v2 · v3 (run 2026-10-04).
The code check is small (15 prompts) and tests that output parses and compiles, not that it is correct. The security multiple-choice section of the harness did not run (0 questions), so no security-knowledge score is claimed yet.
| Stage | Repo |
|---|---|
| Adapter (LoRA) | Taimwe/securecoder-30b-pro-v3 |
| Merged (this repo) | Taimwe/securecoder-30b-pro-v3-merged |
| Training / merge / quantise scripts | Taimwe/securecoder-scripts |
| Architecture | Qwen3MoeForCausalLM (qwen3_moe) |
| Parameters | 30B total, ~3B active |
| Hidden size | 2048 |
| Context length | 262,144 |
| Precision | bfloat16, 13 shards (~56.9 GB) |
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer MODEL = "Taimwe/securecoder-30b-pro-v3-merged" tok = AutoTokenizer.from_pretrained(MODEL)model = AutoModelForCausalLM.from_pretrained( MODEL, torch_dtype=torch.bfloat16, device_map="auto") messages = [{"role": "user", "content": "Write a race-free file watcher in Rust."}]inputs = tok.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=512)print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))A 30B MoE needs a capable GPU. For a smaller download use the Q4_K_M GGUF once published.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer MODEL = "Taimwe/securecoder-30b-pro-v3-merged" tok = AutoTokenizer.from_pretrained(MODEL)model = AutoModelForCausalLM.from_pretrained( MODEL, torch_dtype=torch.bfloat16, device_map="auto") messages = [{"role": "user", "content": "Write a race-free file watcher in Rust."}]inputs = tok.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=512)print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))