llama-cpp: update + re-enable + gemma 4 E4B

2026-04-03 14:06:35 -04:00
parent e765a98487
commit d4d01d63f1
2 changed files with 6 additions and 6 deletions
--- a/services/llama-cpp/llama-cpp.nix
+++ b/services/llama-cpp/llama-cpp.nix
@@ -8,11 +8,11 @@
 }:
 {
  services.llama-cpp = {
-    enable = false;
+    enable = true;
    model = toString (
      pkgs.fetchurl {
-        url = "https://huggingface.co/unsloth/Qwen3.5-9B-GGUF/resolve/main/Qwen3.5-9B-Q4_K_M.gguf";
-        sha256 = "03b74727a860a56338e042c4420bb3f04b2fec5734175f4cb9fa853daf52b7e8";
+        url = "https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF/resolve/main/gemma-4-E4B-it-Q4_K_M.gguf";
+        sha256 = "ced37f54b80068fe65e95c6dd79ac88cddc227e179fd1040b8f751b1e5bdf849";
      }
    );
    port = service_configs.ports.private.llama_cpp.port;