From 42861142dba7968603e2fcedccb9c2373ba60a22 Mon Sep 17 00:00:00 2001 From: Bryan Van Deusen Date: Wed, 27 May 2026 18:09:32 -0400 Subject: [PATCH] chore: remove benchmark notes that were accidentally committed The bench-*.md files got swept into the Phase 8 mega-commit by `git add -A`. They were local working-tree notes the user never intended to track. Co-Authored-By: Claude Opus 4.7 (1M context) --- .remember/tmp/save-session.pid | 2 +- bench-chat.md | 12 ------------ bench-curator-no-think.md | 12 ------------ bench-curator-think-on.md | 10 ---------- bench-gpuhost-chat-cpu.md | 12 ------------ bench-gpuhost-chat-gpu.md | 12 ------------ bench-gpuhost-curator-70b.md | 9 --------- bench-gpuhost-curator-no-think.md | 12 ------------ bench-gpuhost-curator-think-on.md | 10 ---------- 9 files changed, 1 insertion(+), 90 deletions(-) delete mode 100644 bench-chat.md delete mode 100644 bench-curator-no-think.md delete mode 100644 bench-curator-think-on.md delete mode 100644 bench-gpuhost-chat-cpu.md delete mode 100644 bench-gpuhost-chat-gpu.md delete mode 100644 bench-gpuhost-curator-70b.md delete mode 100644 bench-gpuhost-curator-no-think.md delete mode 100644 bench-gpuhost-curator-think-on.md diff --git a/.remember/tmp/save-session.pid b/.remember/tmp/save-session.pid index 423d3c2..e7d4661 100644 --- a/.remember/tmp/save-session.pid +++ b/.remember/tmp/save-session.pid @@ -1 +1 @@ -603480 +604006 diff --git a/bench-chat.md b/bench-chat.md deleted file mode 100644 index d8ba48b..0000000 --- a/bench-chat.md +++ /dev/null @@ -1,12 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.9:11434` -- Hardware mode: CPU only (`num_gpu=0`) -- Think: auto (chat=off, curator=on) - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| qwen3:8b | chat | 5 | 98 | 187 | 2126 | 13.8 | 26 | -| gemma2:9b | chat | 5 | 89 | 184 | 2084 | 11.7 | 22 | -| llama3.2:3b | chat | 5 | 102 | 185 | 1091 | 31.9 | 28 | -| mistral-nemo:12b | chat | 5 | 82 | 228 | 2070 | 10.2 | 19 | diff --git a/bench-curator-no-think.md b/bench-curator-no-think.md deleted file mode 100644 index c024b9f..0000000 --- a/bench-curator-no-think.md +++ /dev/null @@ -1,12 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.9:11434` -- Hardware mode: CPU only (`num_gpu=0`) -- Think: forced OFF - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| qwen3:30b-a3b | curator | 3 | 529 | 183 | 164198 | 17.4 | 2732 | -| qwen3:32b | curator | 3 | 535 | 677 | 136519 | 3.0 | 406 | -| gemma2:27b | curator | 3 | 545 | 392 | 132739 | 3.7 | 451 | -| mistral-small:22b | curator | 3 | 562 | 293 | 105971 | 4.7 | 485 | diff --git a/bench-curator-think-on.md b/bench-curator-think-on.md deleted file mode 100644 index b56e201..0000000 --- a/bench-curator-think-on.md +++ /dev/null @@ -1,10 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.9:11434` -- Hardware mode: CPU only (`num_gpu=0`) -- Think: forced ON - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| qwen3:30b-a3b | curator | 3 | 529 | 147344 | 185694 | 15.6 | 3300 | -| qwen3:32b | curator | 3 | 529 | 98890 | 213817 | 3.1 | 651 | diff --git a/bench-gpuhost-chat-cpu.md b/bench-gpuhost-chat-cpu.md deleted file mode 100644 index d9198fb..0000000 --- a/bench-gpuhost-chat-cpu.md +++ /dev/null @@ -1,12 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.13:11434` -- Hardware mode: CPU only (`num_gpu=0`) -- Think: auto (chat=off, curator=on) - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| qwen3:8b | chat | 5 | 98 | 410 | 4131 | 7.0 | 26 | -| gemma2:9b | chat | 5 | 89 | 410 | 2950 | 8.1 | 21 | -| llama3.2:3b | chat | 5 | 102 | 311 | 1627 | 21.7 | 28 | -| mistral-nemo:12b | chat | 5 | 82 | 458 | 2966 | 7.9 | 19 | diff --git a/bench-gpuhost-chat-gpu.md b/bench-gpuhost-chat-gpu.md deleted file mode 100644 index c2442f4..0000000 --- a/bench-gpuhost-chat-gpu.md +++ /dev/null @@ -1,12 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.13:11434` -- Hardware mode: GPU offload (99 layers) (`num_gpu=99`) -- Think: auto (chat=off, curator=on) - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| qwen3:8b | chat | 5 | 98 | 369 | 1301 | 23.8 | 25 | -| gemma2:9b | chat | 5 | 89 | 426 | 1681 | 22.1 | 24 | -| llama3.2:3b | chat | 5 | 102 | 400 | 1033 | 54.1 | 29 | -| mistral-nemo:12b | chat | 5 | 82 | 446 | 1451 | 19.7 | 18 | diff --git a/bench-gpuhost-curator-70b.md b/bench-gpuhost-curator-70b.md deleted file mode 100644 index e5b569d..0000000 --- a/bench-gpuhost-curator-70b.md +++ /dev/null @@ -1,9 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.13:11434` -- Hardware mode: CPU only (`num_gpu=0`) -- Think: forced OFF - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| llama3.3:70b | curator | 3 | 499 | 1284 | 326662 | 1.1 | 367 | diff --git a/bench-gpuhost-curator-no-think.md b/bench-gpuhost-curator-no-think.md deleted file mode 100644 index 81362b5..0000000 --- a/bench-gpuhost-curator-no-think.md +++ /dev/null @@ -1,12 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.13:11434` -- Hardware mode: CPU only (`num_gpu=0`) -- Think: forced OFF - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| qwen3:30b-a3b | curator | 3 | 529 | 355 | 324789 | 9.8 | 3195 | -| qwen3:32b | curator | 3 | 535 | 813 | 157978 | 2.6 | 404 | -| gemma2:27b | curator | 3 | 545 | 693 | 166996 | 2.7 | 453 | -| mistral-small:22b | curator | 3 | 562 | 386 | 144660 | 3.6 | 490 | diff --git a/bench-gpuhost-curator-think-on.md b/bench-gpuhost-curator-think-on.md deleted file mode 100644 index af3d5bf..0000000 --- a/bench-gpuhost-curator-think-on.md +++ /dev/null @@ -1,10 +0,0 @@ -# Ollama benchmark - -- Server: `http://192.168.0.13:11434` -- Hardware mode: CPU only (`num_gpu=0`) -- Think: forced ON - -| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) | -|---|---|---|---|---|---|---|---| -| qwen3:30b-a3b | curator | 3 | 529 | 261474 | 319287 | 9.8 | 3310 | -| qwen3:32b | curator | 3 | 529 | 127386 | 274725 | 2.5 | 756 |