Unclaimed profileBuilt from public GitHub and Hugging Face activity. Tech2wild has not joined Lounge yet.Claim it
Not on Lounge yet
Tech2wild
founderCreator & Builder. 1M+ on YouTube. Building AI tools that give agents real memory. Founder of 2Wild Agency.
Public projects
Qwen3.8-Flash-Next-NVFP4-DGX-Spark
Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-vocab MTP draft; TP2 SPEED 53.7; TP4 CONTEXT 9M KV pool. Launchers, patch, 40-prompt harness, KV ledger, credits. SGLang TP2 day-0 lane kept.
Python
The-Sparky-Command-Center
Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional RouterOS switch monitoring, and per-model decode/prefill/TTFT/KV cards. Point it at your own hardware.
TypeScriptdashboarddgx-sparkgpu-monitoring
MiMo-V2.5-TP2-1M-NVFP4-KV-2xDGX-Spark
MiMo-V2.5 Omni TP=2 on 2x DGX Spark · 1M context · NVFP4 4-bit KV (~1.97M-token KV pool @ 1M, ~30 tok/s) · 69-eval: thinking-OFF 97.8 beats thinking-ON 90.6 for tool/agent work
Python
DeepSeek-v4-Flash-0731-Vision-DSpark-1M-NVFP4-KV-2x-DGX-Spark
Give DeepSeek V4 Flash eyes. OpenAI-compatible shim + tiny local VLM. Point any harness at one URL and your text-only model accepts images. Zero dependencies.
Python
2Wild-Vision-Mode
Give any blind LLM eyes — on any machine — in one shot. Tiny local VLM (Qwen3.5-0.8B) as an OpenAI-compatible vision service. Mac (MLX) / PC+NVIDIA (llama.cpp) / DGX Spark.
Python
2Wild-Coding-Agent-Latency-Monitor
Live dashboard: fire N parallel streaming coding-agent runs at any OpenAI-compatible endpoint — per-run TTFT/tok-s/E2E, real kill switch, per-GPU metrics, shareable summary. Zero deps.
HTML
Likely stack
ClaudeOpenAILlamavLLMWhisper
