Contact
LOG IN
Sign up
Platform
Models
Inference
Training
Weave
Solutions
Use Cases
Industries
Case Studies
Enterprise
Resources
Docs
Pricing
Contact LOG IN Sign up

OpenPipe Qwen3 14B on W&B Inference

Price per 1M tokens

$0.05 (input)
$0.22 (output)

Parameters

14.8B (total)

Context window

33K

Release date

Apr 2025

READ THE DOCS
SIGN UP

OpenPipe Qwen3 14B inference details

OpenPipe/Qwen3-14B-Instruct is a finetune friendly instruct variant of Qwen3-14B. Qwen3 release does not include a 14B Instruct (non-thinking) model, this fork introduces an updated chat template that makes Qwen3-14B non-thinking by default and be highly compatible with OpenPipe and other finetuning frameworks. The default Qwen3 chat template does not render <think></think> tags on the previous assistant message, which can lead to inconsistencies between training and generation. This version resolves that issue by adding <think></think> tags to all assistant prompts and generation templates to ensure message format consistency during both training and inference. The model retains the strong general capabilities of Qwen3-14B while providing a more finetuning friendly chat template.
 
Created by: OpenPipe
License: apache-2.0
🤗 model card: Qwen3-14B-Instruct
 
 
 
import openai
import weave

# Weave autopatches OpenAI to log LLM calls to W&B
weave.init("<team>/<project>")

client = openai.OpenAI(
    # The custom base URL points to W&B Inference
    base_url='https://api.inference.wandb.ai/v1',

    # Get your API key from https://wandb.ai/authorize
    # Consider setting it in the environment as OPENAI_API_KEY instead for safety
    api_key="<your-apikey>",

    # Optional: Team and project for usage tracking
    project="<team>/<project>",
)

response = client.chat.completions.create(
    model="OpenPipe/Qwen3-14B-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Tell me a joke."}
    ],
)

print(response.choices[0].message.content)

Qwen resources

W&B Inference powered by CoreWeave guide

Get started

Running Qwen3 Coder on W&B Inference

Read the report

AI engineering course: Agents

Take the free course