lovey/README.md

lovey

lovey is my inference server running 2× RTX 3090s. This repo stores and documents its configuration, models and benchmarks, and holds everything needed to rebuild the current setup from bare metal.

Current state (2026-10-26): Proxmox host → one NixOS VM with both GPUs passed through → Strata serving Qwen3.8-Flash-Next IQ3_S on an OpenAI/Anthropic-compatible API, used from pi on my workstation.

 cosmic (workstation)                lovey  192.168.1.53  (Proxmox VE 9.2)
 ┌──────────────────┐     LAN       ┌──────────────────────────────────────────────────────┐
 │ pi coding agent  │──────────────▶│ VM 200 llm-nixos  192.168.1.67  (NixOS 26.05)          │
 │ ~/.pi/agent      │  :8080 + key  │   strata.service ── Qwen3.8-Flash-Next IQ3_S          │
 └──────────────────┘               │   2× RTX 3090 (VFIO), gpu-unlock, 275 W cap           │
                                    │   /models  ◀── virtiofs ── /mnt/models (NVMe XFS)      │
                                    │   gpu-temp-push ──UDP :7777──▶ lovey-fans.service      │
                                    └──────────────────────────────────────────────────────┘

Hardware

Part	Detail
Board	ASUS ROG Maximus Z790 Hero
CPU	Intel i9-14900KS, microcode 0x133, 200 W PL1 / 253 W PL2, Intel default profile
RAM	4× 32 GB = 128 GB DDR5, run at 4800 MT/s JEDEC (unstable at 5200+ with 4 DIMMs)
GPUs	2× Zotac RTX 3090 24 GB at 01:00 and 02:00, PCIe 4.0 x8 each, no NVLink
Boot disk	250 GB SATA SSD (sda): Proxmox only
Data disk	MSI M470 2 TB NVMe, 4K LBA: model store + VM disks
Cooling	Liquid: radiator fans on nct6798 fan2–5 (driven by lovey-fans), pump on fan7, no coolant sensor
NIC	Onboard Intel 2.5G eno2, bridged as vmbr0

Software stack

Layer	What	Docs
Host	Proxmox VE 9.2.21, kernel 7.0.14-pve, pve-no-subscription repos	docs/proxmox-host.md
VM 200	llm-nixos: NixOS 26.05, kernel 6.18, NVIDIA open 595.71, CUDA 13.2	docs/nixos-guest.md
GPU tuning	275 W power cap + gpu-unlock (full-rate FP16/BF16)	docs/nixos-guest.md
Inference	Strata @ 4b9e05a2, Qwen3.8-Flash-Next IQ3_S	docs/strata.md
Client	pi coding agent 1.4.0	docs/pi-client.md
Fans	lovey-fans.py on the host, fed GPU temps by the guest	docs/proxmox-host.md

Current numbers (standard benchmark, idle): prompt ~1,750 tok/s at 4K and ~2,900 tok/s at 16K, decode ~110–131 tok/s, model load ~2 min. See benchmarks/standard.

Repo layout

nixos/        /etc/nixos on llm-nixos (configuration.nix, gpu-unlock.nix, hardware-configuration.nix)
proxmox/      files from lovey, at their real paths (etc/..., usr/local/bin/..., root/...)
strata/       strata-iq3_s.json, the engine config (API key removed)
pi/           ~/.pi/agent/models.json, settings.json and extensions/ for the client (API key removed)
docs/         per-layer notes, rebuild steps and the change log
benchmarks/   live metric snapshots (passive) and later benchmark runs

Secrets are not in this repo (it is public). The Strata API key lives only in /var/lib/strata/api-key and strata-iq3_s.json on the guest; placeholders are marked <...>.

Rebuild order

1. BIOS: memory at 4800 JEDEC, CPU 200/253 W, VT-d on. See proxmox-host.md.
2. Proxmox host: repos, NVMe layout, VFIO, Gluster, fans. proxmox-host.md
3. VM 200 from proxmox/etc/pve/qemu-server/200.conf, then NixOS from nixos/. nixos-guest.md
4. Strata source build + model download. strata.md
5. pi on the workstation. pi-client.md

History

Everything that went wrong and what fixed it is in docs/changelog.md: the Z690 memory-channel fault, the 4-DIMM instability on the Z790, and the pi auto-compaction loop.

Next up

• Strata tuning: the three documented flags gave nothing (results). Next levers: huge pages for the expert arena, a higher power cap for prompt speed.
• Try other quants.
• Planned services as OCI LXCs on the host: SearXNG + degoog, Qdrant, Open WebUI, Tika, Whisper.