GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
dracko14
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
dracko14
Model Tree
Jackrong/Qwen3.5-4B-Neo
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
| Attribute | Value |
|---|---|
| Base Model | Qwen 3.5 4B |
| Parameters | 4B |
| Context Length | 32K |
| Architecture | qwen3_5 |
| Format | FP16 (sharded, 8 files) + GGUF Q4_K_M |
| Fusion Method | SLERP (50% Qwen 3.5 + 50% Neo) |
markdown
Qwen 3.5 4B (multimodal base)|├── SLERP ──→ 🧬 Myth 4B|Qwen3.5-4B-Neo (reasoning expert)
Myth inherits:
Unlike most merges that use mergekit, Myth 4B was merged using a custom-built fusion engine:
markdown
myth_fusion.py — Custom SLERP Engine• Reads safetensors directly (no transformers dependency)• Processes one tensor at a time (low memory footprint)• Saves in shards (8 shards × ~100 tensors each)• Supports any model architecture• No GPU required
738 tensors were merged in 2 stages, with shard-based saving to prevent OOM on 8GB RAM hardware.
| File | Size | Description |
|---|---|---|
model-*.safetensors (×8) | 8.8 GB total | FP16 model weights (sharded) |
Myth-4B-Q4_K_M.gguf | 2.78 GB | Quantized GGUF (Q4_K_M) |
myth_system_prompt.md | 5 KB | Custom system prompt (Claude Fable 5-inspired) |
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("dracko14/Myth-4B",torch_dtype="auto",device_map="auto",trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained("dracko14/Myth-4B",trust_remote_code=True)messages = [{"role": "system", "content": "You are Myth, a helpful AI assistant."},{"role": "user", "content": "Write a Python function for binary search."},]prompt = tokenizer.apply_chat_template(messages, tokenize=False)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=200)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
bash
# Download GGUFwget https://huggingface.co/dracko14/Myth-4B/resolve/main/Myth-4B-Q4_K_M.gguf# Run with llama.cpp./llama-cli -m Myth-4B-Q4_K_M.gguf -p "Hello" -n 256# Or with Ollama (create Modelfile first)echo "FROM ./Myth-4B-Q4_K_M.gguf" > Modelfileollama create myth -f Modelfileollama run myth
Myth includes a custom system prompt inspired by Claude Fable 5: 📄 myth_system_prompt.md
Benchmarks coming soon. Myth 4B inherits Qwen 3.5 4B's strong baseline with enhanced reasoning from Neo.
| Detail | Value |
|---|---|
| Compute | 8GB RAM VPS (CPU only) |
| Merge Time | ~15 minutes (738 tensors) |
| Quantization | llama.cpp (162 seconds) |
| Upload | ~10 minutes |
| Total Cost | $0 (free VPS + free HuggingFace) |
MIT — open for all use cases.
Built with ❤️ using myth_fusion.py — a custom SLERP fusion engine