darmanandClaude Sonnet 5
713d91d5fc
Follow-up to e5ba1bf — that commit only staged the deleted module file.
Drops the flake module import, opencode_go_api_key/telegram_bot_token
secrets, and the stale hermes-agent.nix cross-reference in ollama's
context_length comment.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
148 lines
6.3 KiB
Nix
148 lines
6.3 KiB
Nix
# ---- TERRA ----
|
|
{ config, pkgs, lib, inputs, ... }:
|
|
|
|
let
|
|
unstable = import inputs.nixpkgs-unstable {
|
|
inherit (pkgs.stdenv.hostPlatform) system;
|
|
config = pkgs.config;
|
|
};
|
|
in
|
|
{
|
|
imports = [
|
|
./hardware-configuration.nix
|
|
./disk-config.nix
|
|
./secrets.nix
|
|
../../common.nix
|
|
../../services/containers.nix
|
|
../../services/vpn/tailscale.nix
|
|
../../services/desktop/desktop-hyprland.nix
|
|
../../services/desktop/desktop-apps.nix
|
|
../../services/desktop/librechat.nix
|
|
];
|
|
|
|
networking.hostName = "terra";
|
|
|
|
services.flatpak = {
|
|
enable = true;
|
|
remotes = [{ name = "flathub"; location = "https://dl.flathub.org/repo/flathub.flatpakrepo"; }];
|
|
packages = [
|
|
{ appId = "com.github.tchx84.Flatseal"; origin = "flathub"; }
|
|
{ appId = "com.blitzfc.qbz"; origin = "flathub"; }
|
|
{ appId = "com.discordapp.Discord"; origin = "flathub"; }
|
|
{ appId = "org.telegram.desktop"; origin = "flathub"; }
|
|
{ appId = "com.bambulab.BambuStudio"; origin = "flathub"; }
|
|
];
|
|
};
|
|
|
|
environment.systemPackages = [ unstable.proton-pass-cli ];
|
|
|
|
# ---- nix-ld: lets generic dynamically-linked Linux binaries run as-is —
|
|
# needed for editor extensions (Zed/VSCode LSPs, debuggers, etc.) that
|
|
# download prebuilt binaries not built for NixOS. See
|
|
# https://nix.dev/permalink/stub-ld ----
|
|
programs.nix-ld.enable = true;
|
|
|
|
# ---- home-manager (user-level config for darman) ----
|
|
home-manager.useGlobalPkgs = true;
|
|
home-manager.useUserPackages = true;
|
|
home-manager.backupFileExtension = "hm-bak";
|
|
home-manager.extraSpecialArgs = { inherit unstable inputs; };
|
|
home-manager.users.darman = import ./home.nix;
|
|
|
|
# ---- Boot (UEFI) ----
|
|
boot.loader.systemd-boot.enable = true;
|
|
boot.loader.efi.canTouchEfiVariables = true;
|
|
hardware.cpu.amd.updateMicrocode = true;
|
|
|
|
# mercury (aarch64) is built/flashed from here. Without this, `nix build`
|
|
# for it dies with "platform mismatch" — no qemu binfmt handler registered
|
|
# and aarch64-linux missing from nix.settings.extra-platforms. This module
|
|
# sets up both (see CLAUDE.md's aarch64 gotcha).
|
|
boot.binfmt.emulatedSystems = [ "aarch64-linux" ];
|
|
|
|
# ---- GPU (Radeon RX 6800 XT / Navi 21) ----
|
|
hardware.enableRedistributableFirmware = true;
|
|
boot.initrd.kernelModules = [ "amdgpu" ];
|
|
|
|
# /dev/dri/renderD128 is root:render 0660, so rootless podman containers can
|
|
# only reach the GPU if the *host* user is in render. Needed by the Vulkan
|
|
# whisper.cpp/llama.cpp containers in ~/Data/Dev/repos/content-trigger-scanner.
|
|
users.users.darman.extraGroups = [ "render" "video" ];
|
|
|
|
# ---- ollama (local LLM server, ROCm on the 6800 XT) ----
|
|
# Navi 21 is gfx1030 — officially supported by ROCm, so no
|
|
# rocmOverrideGfx/HSA_OVERRIDE_GFX_VERSION needed (that's for gpus ROCm
|
|
# doesn't recognize, e.g. RDNA1/gfx101x). The upstream module runs the
|
|
# service under DynamicUser with SupplementaryGroups=["render"] and
|
|
# DeviceAllow for char-kfd/char-drm/char-fb already, so unlike jellyfin's
|
|
# static user it needs no extraGroups wiring here.
|
|
services.ollama = {
|
|
enable = true;
|
|
package = pkgs.ollama-rocm;
|
|
# keep in sync with services/desktop/librechat.nix's endpoints.custom
|
|
# default model — LibreChat's config schema needs a non-empty default
|
|
# even though fetch=true replaces it with whatever's actually pulled.
|
|
# gemma4:12b: general chat/coding daily driver, fits fully in 16G VRAM —
|
|
# also doubles as the memory-extraction agent (see librechat.nix): a
|
|
# 3b model (llama3.2:3b, dropped) couldn't reliably tell the user's
|
|
# stated facts apart from its own boilerplate, e.g. saving "I am an AI
|
|
# assistant with tool calling capabilities" as the user's personal_info
|
|
# after "Hi I'm Erik Simon". Reusing gemma4:12b for both roles also means
|
|
# no second model needs to swap into VRAM while it's already the active
|
|
# chat model.
|
|
# qwen3.6:35b-a3b: MoE (3B active/36B total), ~24GB Q4_K_M — doesn't fit
|
|
# in VRAM alone, so ollama offloads the inactive experts to CPU RAM.
|
|
# Sparse activation makes that far less painful than it'd be for a dense
|
|
# model this size, but still expect it to run slower than the two above.
|
|
loadModels = [ "gemma4:12b" "qwen3.6:35b-a3b" ];
|
|
# Ollama truncates context far below the model's real window unless
|
|
# told otherwise (the OpenAI-compat /v1 route it's reached through has
|
|
# no way to set this per-request). 131072 chosen as the practical
|
|
# ceiling after load-testing with real prompts, not just idle
|
|
# `ollama ps` checks:
|
|
# 32768 (31.6k-token prompt) and 65536 (40.8k-token prompt) both stayed
|
|
# 100% GPU with VRAM barely moving (~10.1G / ~10.67G of 16G) — KV cache
|
|
# cost barely grows with context, likely sliding-window/local attention
|
|
# on most of gemma4:12b's layers. At 131072 that stopped being true: a
|
|
# ~108k-token prompt pushed VRAM to ~11.4G/16G (still 100% GPU, no CPU
|
|
# spillover, negligible GTT) but with visibly shrinking headroom, and
|
|
# prefill throughput measurably dropped (~490 -> ~460 tok/s) over just
|
|
# the last 13k tokens — filling the full window would take minutes of
|
|
# pure prompt processing. Stopped here rather than push further: next
|
|
# doubling would risk CPU spillover under any concurrent GPU load
|
|
# (desktop compositor, jellyfin transcode) for diminishing benefit.
|
|
environmentVariables.OLLAMA_CONTEXT_LENGTH = "131072";
|
|
};
|
|
|
|
# ---- Dev-data disks — NOT in disko, mounted read-write, never wiped ----
|
|
fileSystems."/mnt/hdd_01" = {
|
|
device = "/dev/disk/by-uuid/b8445126-ec6d-4f88-818a-d9e13031d9a4";
|
|
fsType = "ext4";
|
|
options = [ "nofail" ];
|
|
};
|
|
fileSystems."/mnt/ssd_01" = {
|
|
device = "/dev/disk/by-uuid/6ca18a9f-27bc-4e58-aea8-de43a0d0ed5d";
|
|
fsType = "ext4";
|
|
options = [ "nofail" ];
|
|
};
|
|
|
|
# jupiter's samba share (services/network/samba.nix) — mounted on demand so
|
|
# terra doesn't stall boot/login when jupiter is off or unreachable.
|
|
fileSystems."/mnt/jupiter" = {
|
|
device = "//jupiter/data";
|
|
fsType = "cifs";
|
|
options = [
|
|
"credentials=${config.sops.templates."jupiter-smb.credentials".path}"
|
|
"uid=1000"
|
|
"gid=100"
|
|
"nofail"
|
|
"x-systemd.automount"
|
|
"x-systemd.idle-timeout=60"
|
|
"x-systemd.mount-timeout=10s"
|
|
"_netdev"
|
|
];
|
|
};
|
|
|
|
system.stateVersion = "26.05";
|
|
}
|