RunPod AI Assistant
Qwen2.5-72B · A100 SXM 80GB · GPTQ Int4
Tools, code execution, file access — সব এখানে।
Temp0.70
Tokens2048
Workspace
Loading…
← ফাইলে ক্লিক করো
▶ Run করো
Pod Status
Namefrozen_coral_rook
Status—
vLLM API—
GPUA100 SXM 80GB
Session Cost
$0.00
this session
Uptime—
Rate$1.79/hr
ModelQwen2.5-72B-Int4
Hybrid Router
Port9000
Status—
ModeLocal Only
Loaded Model
QuantGPTQ Int4
Context65,536 tokens
FrameworkvLLM
Proxyrunpod.net
Chat History
Loading…
Settings
0.70
2048
Enable function calling (run_python, read_file, bash…)