GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
TaimoorSiddiqui
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
TaimoorSiddiqui
Model Tree
TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36
Input Modalities
Output Modalities
Supported Functionality
This repo is prepared for the Featherless Hugging Face ingestion requirements:
model.safetensors.index.json.FP16.TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36; no embedding resize or tensor-shape variation is introduced.Featherless serves Qwen-family models at up to 16k context. The source config may advertise a larger native context, but prompts plus completions should stay within Featherless' served context limit.
The tokenizer chat template is included in tokenizer_config.json and chat_template.jinja. Tool calls are trained and documented as JSON inside <tool_call> tags:
xml
<tool_call>{"name":"tool_name","arguments":{"argument_name":"value"}}</tool_call>
After a <tool_response> turn, clients should continue generation until the assistant provides a final answer.