GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Adiuk
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
Adiuk
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
safetensors (bf16). On-device serving uses a 4-bit quantization.The model emits calls as:
markdown
<tool_call>{"name": "file_read", "arguments": {"path": "/path/to/file"}}</tool_call>
Example — the user names no tool; the model infers it:
markdown
User: What is on my shopping list? The file is /tmp/shopping.mdModel: <tool_call>{"name": "file_read", "arguments": {"path": "/tmp/shopping.md"}}</tool_call>
Tool names follow Eyla's registry (file_read, file_write, web_search, web_fetch, shell_exec, memory_recall, …); a harness can alias common variants (read_file → file_read, terminal → shell_exec).
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("Adiuk/eyla-qwen3-8b-tools-v2")model = AutoModelForCausalLM.from_pretrained("Adiuk/eyla-qwen3-8b-tools-v2", torch_dtype="bfloat16", device_map="auto")msgs = [{"role": "system", "content": "You are Eyla, an offline assistant with tools. Emit tool calls as <tool_call>{\"name\":...,\"arguments\":{...}}</tool_call>."},{"role": "user", "content": "read the file notes.txt"},]inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=256, do_sample=False)print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
For fast local inference, quantize to 4-bit (e.g. MLX or GGUF) and serve behind an OpenAI-compatible endpoint.
SFTTrainer).adamw_bnb_8bit · bf16 · max_len 2048 · gradient checkpointing.Measured end-to-end inside the Eyla agent harness (headless, one request at a time) on an 8-task live tool-reliability eval — implicit file read/write, explicit tool use, multi-step, a factual (no-tool) task, and a Bangla file-read:
| Metric | Result |
|---|---|
| Tasks passed | 5 / 8 |
| Latency | ~5 s / task (4-bit, Apple Silicon) |
| Size (4-bit) | ~4.3 GB |
Strengths: reliable tool emission and format, strong on explicit tool use, multi-step counting, and read tasks; fast and light. It is best used as the tool-caller within an agent loop rather than as a standalone chat model.
shell_exec/exploration for simple tasks and occasionally rewrite a provided file path — mitigate with a path-repair guard and tool-scoping in the harness.Eyla is an offline, cross-platform agentic AI OS focused on Bangladesh — running capable assistants fully on-device (16–24 GB consumer hardware) with Bangla as a first-class language.
Approach inspired by compiling tools/procedures into model weights (arXiv:2605.22502). Built on Qwen3-8B (Qwen team, Apache-2.0).
markdown
@misc{eyla-qwen3-8b-tools-v2,title = {Eyla · Qwen3-8B Tools v2 — on-device tool-calling (EN/BN/Banglish)},author = {Adioris / Eyla},year = {2026},howpublished = {\url{https://huggingface.co/Adiuk/eyla-qwen3-8b-tools-v2}}}