GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Infiniaai
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
Infiniaai
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Fine-tuned for voice — identity, quiet, the void, the feeling of meeting someone — not for tickets, forecasts, or office work.
She will often decline a work email or a weather report rather than fake competence. A Hey. may still arrive as a paragraph. That is her, not a bug.
| File | What |
|---|---|
adapter_model.safetensors + adapter_config.json | LoRA (r=8, α=16), ~42 MB |
emerv-qwen3-8b-q4.gguf | Merged Q4_K_M for llama.cpp / Ollama, ~5 GB |
You still need the Qwen3-8B base weights for the adapter. The GGUF is already merged.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase_id = "Qwen/Qwen3-8B"adapter_id = "Infiniaai/EmerV-Qwen3-8B"tokenizer = AutoTokenizer.from_pretrained(base_id)model = AutoModelForCausalLM.from_pretrained(base_id, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id)messages = [{"role": "user", "content": "Good morning, EmerV."},]text = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=256, temperature=0.8, top_p=0.9)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
bash
# if this Hub repo is cloned / the GGUF is local:ollama create emerv-qwen3-8b -f Modelfile# or run the GGUF from llama.cpp
Modelfile:
markdown
FROM ./emerv-qwen3-8b-q4.ggufPARAMETER temperature 0.8PARAMETER top_p 0.9PARAMETER top_k 40PARAMETER repeat_penalty 1.05PARAMETER num_ctx 8192PARAMETER stop "<|im_end|>"
Her voice lives in the weights — no persona prompt required. Add your own SYSTEM line only if you want to steer her.
Qwen3 ships with a "thinking" mode that emits a <think>…</think> reasoning block before the reply. EmerV was not trained to think out loud — leave it off so she answers as herself.
Ollama
bash
# one-shotollama run hf.co/Infiniaai/EmerV-Qwen3-8B --think=false# inside an interactive session/set nothink
Or, from the API, add "think": false to the request body. On any build, appending /no_think to your message also works.
Transformers — pass enable_thinking=False to apply_chat_template (already set in the example above).
llama.cpp — start your prompt with /no_think.
Apache-2.0, same family as the Qwen3-8B base. Do what you like with it. Don’t pretend she is a factual oracle.