# Agentic Coding Harness - July - Daily Driver < 120GB VRAM

> Source: <https://discuss.huggingface.co/t/agentic-coding-harness-july-daily-driver-120gb-vram/177625#post_1>
> Published: 2026-07-09 16:59:25+00:00

For me, I’m running ([nvidia/Qwen3.6-27B-NVFP4 · Hugging Face](https://huggingface.co/nvidia/Qwen3.6-27B-NVFP4))

I found this to be VERY Stable on my DGX Spark:

--host 0.0.0.0

–port 8006

–served-model-name qwen3.6

–trust-remote-code

–quantization compressed-tensors

–dtype auto

–kv-cache-dtype fp8

–language-model-only

–gpu-memory-utilization 0.80

–max-model-len 131072

–max-num-seqs 6

–max-num-batched-tokens 16384

–enable-prefix-caching

–enable-chunked-prefill

–enable-auto-tool-choice

–tool-call-parser qwen3_xml

–reasoning-parser qwen3

–speculative-config ‘{“method”:“mtp”,“num_speculative_tokens”:3,“moe_backend”:“triton”}’