benchmarks: add local model support and Node version note (#63)

Adds benchmarks/benchmark-local.py (Ollama-based local runner), a results writeup, and a Node version note. Thanks @mandavillivijay.
2026-06-15 15:27:11 +02:00
parent 60a75f8159
commit 386f95734a
3 changed files with 241 additions and 0 deletions
@@ -0,0 +1,68 @@
+# Local model benchmark: llama3.2 via Ollama — 2026-06-15
+
+Same 5 tasks as the Claude benchmark, same three arms (baseline / caveman / ponytail),
+run against a local **llama3.2:latest** (3.2B, Q4_K_M) via Ollama on a Windows 11 machine.
+n=1 per cell. Tooling: `benchmarks/benchmark-local.py` (no promptfoo needed).
+
+## Results
+
+**Code LOC**
+
+| arm | email | debounce | csv-sum | countdown | rate-limit | **TOTAL** |
+|---|--:|--:|--:|--:|--:|--:|
+| baseline | 13 | 13 | 38 | 44 | 32 | **140** |
+| caveman | 16 | 12 | 5 | 45 | 28 | **106** |
+| ponytail | 18 | 21 | 7 | 38 | 49 | **133** |
+
+**Time (seconds)**
+
+| arm | email | debounce | csv-sum | countdown | rate-limit | **TOTAL** |
+|---|--:|--:|--:|--:|--:|--:|
+| baseline | 52.6 | 37.2 | 63.4 | 65.2 | 71.0 | **289.4** |
+| caveman | 79.6 | 54.4 | 28.3 | 71.4 | 61.0 | **294.7** |
+| ponytail | 99.7 | 71.0 | 25.4 | 74.8 | 97.3 | **368.2** |
+
+**LOC vs baseline**
+
+| arm | total LOC | vs baseline |
+|---|--:|---|
+| caveman | 106 | −24% |
+| ponytail | 133 | −5% |
+
+## Key findings
+
+**Ponytail does not transfer to llama3.2.** On 3 of 5 tasks (email: 13→18, debounce: 13→21,
+rate-limit: 32→49) ponytail produced *more* code than the no-skill baseline. Total LOC
+reduction was −5% vs the 80–94% seen on Claude. Response time increased by +27% (368s vs
+289s) rather than the 3–6× speedup seen on Claude.
+
+**Caveman outperformed ponytail on this model** (−24% LOC, similar time to baseline).
+Caveman's rules are simpler prose instructions that a small model can follow more reliably;
+ponytail's multi-step decision ladder requires a stronger instruction-follower.
+
+**Why this happens:** Ponytail is a prompt-engineering skill calibrated on Claude models,
+which are specifically trained to follow detailed system instructions. A 3.2B quantised model
+partially absorbs the ponytail rules and then adds extra prose *justifying* its choices —
+paying the complexity cost without getting the minimalism benefit.
+
+## Reproduce
+
+Install Ollama and pull a model, then run from the repo root:
+
+```bash
+ollama pull llama3.2
+python benchmarks/benchmark-local.py --model llama3.2
+```
+
+Optional flags:
+
+```
+--repeat N       Runs per cell; median is reported (default: 1)
+--ollama-url URL Ollama base URL (default: http://localhost:11434)
+```
+
+## Takeaway
+
+The benchmark claims in the README are accurate for the models tested (Haiku, Sonnet, Opus).
+For local/small models, expect significantly smaller — or even negative — gains until
+instruction-following capability reaches a threshold comparable to Claude Haiku or better.