docs: remove V100 from GPU bakeoff

V100 data was degraded by SDXL co-residence on CT 167 (31/32 GB VRAM
occupied, Gemma 4 models forced 95% onto CPU). Rather than ship a
prominent caveat, drop the V100 column entirely so the doc reports
only apples-to-apples measurements. V100 can be added back once an
isolated run is possible.

Removed: V100 column from TL;DR and per-model tables, hardware row,
caveat section, and associated raw JSONs under runs/pve197/. Harness
config keeps pve197 in HOSTS for future re-runs.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

README.md

@@ -18,7 +18,7 @@ Research corpus and implementation guidance for Google Gemma 4, based on product
 | `docs/openwebui-setup.md` | How to configure Gemma 4 inside OpenWebUI — per-setting reference, two ready-to-bake Workspace Model profiles (chat + extract), and a symptom→cause troubleshooting table mapped back to GOTCHAS.md. Assumes Ollama + OpenWebUI are already running. | When setting up or debugging a Gemma 4 model in OpenWebUI, or handing the front-end config to someone else |
 | `docs/reference/bakeoff-2026-04-18.md` | CLI-coding-agent bakeoff on 3090 Ti. **Rounds 1/2 misidentified the cause; Round 3 (the correct one): `think: false` silent-stops gemma4:26b at certain multi-turn states on 32K context.** 31B and Qwen3-Coder robust to the flag. Harness at `scripts/bakeoff/` | When deciding which model to back a CLI agent with, writing a custom agent payload, or debugging a silent tool-call halt |
 | `docs/reference/mort-bakeoff-2026-04-18.md` | mort-bot-specific `think=true` vs `think=false` bakeoff on mort's actual loop shape (gemma4:26b, num_ctx=8192). **Thinking does NOT accumulate in context on Ollama 0.20.4** — strips it from serialized history. Both settings behave identically on step counts, tool counts, wall clock. Harness at `scripts/mort-bakeoff/` | When deciding mort-bot's THINK env var, or when someone claims "think=true eats context" without pinning an Ollama version |
-| `docs/reference/gpu-bakeoff-2026-04-20.md` | Cross-GPU throughput bakeoff: steel141 RTX 3090 Ti vs pve197 V100 vs matt-strix (AMD Strix Halo). **3090 Ti wins decode decisively (128 tok/s on 26B MoE). Strix gets ~42% of that on ~25% of the bandwidth. V100 numbers are degraded because SDXL on CT 167 occupies 31/32 GB of its VRAM.** Also quantifies the MoE vs dense gap: 26B decodes ~4.7× faster than 31B on every card. Harness at `scripts/gpu-bakeoff/` | When choosing which host to run a Gemma 4 workload on, or deciding whether the V100 needs isolated for a given job |
+| `docs/reference/gpu-bakeoff-2026-04-20.md` | Cross-GPU throughput bakeoff: steel141 RTX 3090 Ti vs matt-strix (AMD Strix Halo). **3090 Ti wins decode decisively (128 tok/s on 26B MoE). Strix gets ~42% of that on ~25% of the bandwidth.** Also quantifies the MoE vs dense gap: 26B decodes ~4.7× faster than 31B on both cards. Harness at `scripts/gpu-bakeoff/` | When choosing which host to run a Gemma 4 workload on |
 | `tooling/` | **Canonical upstream tooling** — real scripts, notebooks, model cards, and configs pulled from Google / HF / framework maintainers (147 files). Subdirs: `google-official/`, `huggingface/`, `inference-frameworks/`, `gemma-family/`, `fine-tuning/`. See `tooling/README.md` for index and findings that update the older `CORPUS_*` docs | When you need authoritative source material — model cards, chat templates, fine-tuning recipes, serving commands for vLLM / llama.cpp / MLX, or to scope a specialized sibling (ShieldGemma, EmbeddingGemma, etc.) |
 
 ## Source Projects

docs/reference/gpu-bakeoff-2026-04-20.md

@@ -1,7 +1,7 @@
-# GPU Bakeoff — Gemma 4 Throughput Across Three Architectures
+# GPU Bakeoff — Gemma 4 Throughput: 3090 Ti vs Strix Halo
 
 **Date:** 2026-04-20
-**Host matrix:** steel141 (RTX 3090 Ti) · pve197 CT 105 (Tesla V100) · matt-strix (AMD Strix Halo iGPU)
+**Host matrix:** steel141 (RTX 3090 Ti) · matt-strix (AMD Strix Halo iGPU)
 **Models:** `gemma4:26b` (MoE Q4_K_M) · `gemma4:31b-it-q4_K_M` (dense Q4_K_M)
 **Harness:** `scripts/gpu-bakeoff/harness.py`
 **Raw data:** `scripts/gpu-bakeoff/runs/`
@@ -14,12 +14,6 @@
 |-----|------------------|--------------------|-----------------------|
 | **RTX 3090 Ti** (steel141) | **128 tok/s** | **27 tok/s** | **23,849 tok/s** |
 | **AMD Strix Halo iGPU** (matt-strix) | 54 tok/s (42%) | 11 tok/s (39%) | 14,326 tok/s (60%) |
-| **Tesla V100** (pve197) ⚠ | 8 tok/s (6%) | 1.6 tok/s (6%) | 2,696 tok/s (11%) |
-
-> ⚠ **V100 numbers reflect degraded conditions — SDXL on CT 167 occupies
-> 31.7 / 32.7 GB VRAM, forcing Ollama's Gemma 4 models 95% onto CPU.**
-> Under isolation, V100 should land between 3090 Ti and Strix based on
-> raw specs (HBM2 ~900 GB/s). See § "V100 caveat" for the evidence.
 
 ### Headline findings
 
@@ -33,10 +27,6 @@
 3. **Strix Halo punches above its bandwidth.** Gets 42 % of 3090 Ti
    decode speed on only ~25 % of the memory bandwidth (~256 GB/s vs
    ~1008 GB/s) — good SIMD utilization, especially on the MoE model.
-4. **V100 is held back by shared VRAM.** Its spec should put it closer
-   to 3090 Ti than to Strix, but coresident SDXL crowds out Ollama's
-   layer offload. The V100 column in this doc is an *as-is* reading,
-   not a *peak-capability* reading.
 
 ---
 
@@ -45,7 +35,6 @@
 | Host | GPU | VRAM | Bandwidth | Compute cap | Notes |
 |------|-----|------|-----------|-------------|-------|
 | steel141 | RTX 3090 Ti | 24 GB GDDR6X | ~1008 GB/s | 8.6 (Ampere) | Seth's workstation. Also has a GTX 1660 SUPER as aux display card — not used for inference. Ollama on 127.0.0.1:11434. |
-| pve197 CT 105 | Tesla V100-PCIE-32GB | 32 GB HBM2 | ~900 GB/s | 7.0 (Volta) | LXC with GPU passthrough. Ollama on 192.168.0.179:11434. **Coresident with CT 167 ai-visualizer (SDXL) which consumes most of the VRAM.** |
 | matt-strix | AMD Strix Halo (Radeon 890M iGPU + XDNA 2 NPU) | Shared LPDDR5X | ~256 GB/s | — | Unified memory lets it fit models a 24 GB card can't. Ollama on 100.117.155.64:11434 via Tailscale. |
 
 ---
@@ -65,10 +54,6 @@
   jitter are excluded from the rates.
 - Median of the 3 measurement runs is reported in tables; min/max are in
   the raw JSON.
-- **No network-introduced variance** — all three hosts exposed HTTP
-  Ollama endpoints (matt-strix via Tailscale). The timings reported are
-  computed server-side from `prompt_eval_count / prompt_eval_duration`
-  and `eval_count / eval_duration`.
 
 ---
 
@@ -79,10 +64,10 @@
 Decode is the metric that matters most for interactive LLM use — it's
 the speed of token generation after the prompt has been processed.
 
-| Model | 3090 Ti | V100 ⚠ | Strix Halo |
+| Model | 3090 Ti | Strix Halo |
-|-------|---------|-------|------------|
+|-------|---------|------------|
-| gemma4:26b (MoE, ~4 B active) | **128.20** | 8.34 | 53.86 |
+| gemma4:26b (MoE, ~4 B active) | **128.20** | 53.86 |
-| gemma4:31b (dense, 31.3 B active) | **27.15** | 1.55 | 10.64 |
+| gemma4:31b (dense, 31.3 B active) | **27.15** | 10.64 |
 
 ### Prefill rate (tok/s, long ~500-token prompt, median)
 
@@ -91,52 +76,20 @@ before decode begins. Batched per-token, so short-prompt prefill numbers
 are noisy (dominated by fixed overhead — see raw JSON for those); the
 long-prompt numbers below are the ones to reason from.
 
-| Model | 3090 Ti | V100 ⚠ | Strix Halo |
+| Model | 3090 Ti | Strix Halo |
-|-------|---------|-------|------------|
+|-------|---------|------------|
-| gemma4:26b (long) | **23,849** | 2,696 | 14,326 |
+| gemma4:26b (long) | **23,849** | 14,326 |
-| gemma4:31b (long) | **7,716** | 436 | 3,278 |
+| gemma4:31b (long) | **7,716** | 3,278 |
 
 ### Short-prompt prefill (for reference)
 
 On a 15-token prompt, prefill tokens/sec is meaningless — prompt is too
 small to amortize overhead. Included only to confirm no regression.
 
-| Model | 3090 Ti | V100 ⚠ | Strix Halo |
+| Model | 3090 Ti | Strix Halo |
-|-------|---------|-------|------------|
+|-------|---------|------------|
-| gemma4:26b (short) | 2,063 | 240 | 1,276 |
+| gemma4:26b (short) | 2,063 | 1,276 |
-| gemma4:31b (short) | 661 | 41 | 292 |
+| gemma4:31b (short) | 661 | 292 |
-
----
-
-## V100 caveat — why the numbers are degraded
-
-Mid-bakeoff I probed `GET /api/ps` on pve197 while the V100's Q8 MoE was
-loaded:
-
-```
-gemma4:26b-a4b-it-q8_0   size: 30.5 GB   size_vram: 1.57 GB
-```
-
-**Only 1.57 GB of the 30.5 GB model is actually resident on the V100;**
-the other 28.9 GB is running on CPU via Ollama's CPU-offload fallback.
-`nvidia-smi` corroborated: 31,754 / 32,768 MiB used, 0 % utilization
-at probe time. That remaining ~29 GB of VRAM isn't free — it's held by
-the SDXL pipeline on CT 167 (claude-avatar + ai-visualizer).
-
-Impact on every V100 number in this doc:
-- `gemma4:26b` Q4_K_M is 18 GB — doesn't fit in the ~1 GB of headroom
-  SDXL leaves, so it runs largely on CPU. Observed 8.3 tok/s is
-  consistent with CPU inference of a MoE 26B Q4 model.
-- `gemma4:31b` Q4_K_M is 19.9 GB — same fate. Observed 1.55 tok/s is
-  consistent with dense 31B on CPU (dense kills you on CPU; only
-  ~4 B params activate on the MoE, so the MoE suffers less).
-- The Q8 variant (28 GB) never had a chance on the V100 while SDXL is
-  loaded. Bakeoff did not attempt it.
-
-**To get isolated V100 numbers**, stop SDXL on CT 167 (or stop CT 167
-entirely) and re-run `scripts/gpu-bakeoff/harness.py --host pve197`.
-Left as a follow-up — whether that's worth the ai-visualizer
-interruption is a judgment call. See "Open questions" below.
 
 ---
 
@@ -162,10 +115,10 @@ smaller. For interactive chat this is decisive: Seth's `mort-bot`
 running `gemma4:26b` gets ~4.7× the responsiveness it would on
 `gemma4:31b`, even though the models are near-equal in total params.
 
-Why the ratio holds on every GPU: **memory bandwidth is the bottleneck**
+Why the ratio holds on both GPUs: **memory bandwidth is the bottleneck**
-across all three cards. Strix gets 42 % of 3090 Ti on 26B and 39 % of
+on both cards. Strix gets 42 % of 3090 Ti on 26B and 39 % of 3090 Ti on
-3090 Ti on 31B — identical ratios — because it has ~25 % of the
+31B — nearly identical ratios — because it has ~25 % of the bandwidth
-bandwidth and matches or exceeds proportionally.
+and matches or slightly exceeds proportionally.
 
 ---
 
@@ -176,44 +129,31 @@ bandwidth and matches or exceeds proportionally.
     comfortable for real-time responses.
   - Fallback: **Strix Halo** — 54 tok/s is usable. Benefit is unified
     memory can host larger models the 24 GB 3090 Ti can't.
-  - Avoid: V100 *while SDXL is coresident.* Without SDXL it should be
-    competitive.
 
 **Long-context / prompt-heavy workloads (prefill-heavy).**
   - Primary: **3090 Ti** again — 23,849 tok/s prefill means a
     500-token prompt ingests in ~21 ms.
   - Strix at 14,326 tok/s is ~35 ms — still interactive.
 
-**Running models that don't fit elsewhere.**
+**Running models that don't fit on discrete cards.**
-  - Strix Halo. Unified LPDDR5X can hold 80 GB+ models that 24 GB and
+  - Strix Halo. Unified LPDDR5X can hold 80 GB+ models that a 24 GB
-    32 GB discrete cards can't — at the cost of lower bandwidth.
+    3090 Ti can't — at the cost of lower bandwidth.
   - The largest model tested here (`gemma4:31b` Q4 at 19.9 GB) fits
-    all three. Q8 variants (28 GB+) only fit the V100 and Strix.
+    both. Q8 variants (28 GB+) only fit Strix in this matrix.
 
 **Fine-tuning / training.**
   - Not measured here. 3090 Ti's 24 GB limits batch size on 20 B+
-    models; V100's 32 GB HBM2 is much more forgiving *if* isolated.
+    models.
 
 ---
 
 ## Open questions / follow-ups
 
-1. **Isolated V100 re-run.** Stop SDXL, re-run the harness. Expected
+1. **Strix max-model fit.** Strix can host models that wouldn't fit the
-   outcome: V100 decode lands between 3090 Ti and Strix (probably
+   3090 Ti. A follow-up would pull a larger model (70 B+ quantized) on
-   ~70-90 tok/s on 26B given HBM2 bandwidth ~900 GB/s vs 3090 Ti's
+   matt-strix and measure the Strix-only performance ceiling.
-   ~1008 GB/s). That would settle the V100's actual rank.
+2. **Q8 vs Q4 on Strix.** Same model, two quantizations — quality/speed
-2. **V100 Q8 baseline.** `gemma4:26b-a4b-it-q8_0` (28 GB) is the Q8
+   tradeoff characterization.
-   MoE variant Seth pulled on pve197 — worth measuring once isolated.
-   Q8 vs Q4 quality/speed tradeoff for the same model would be useful.
-3. **Strix max-model fit.** Strix can probably host models that
-   wouldn't fit the discrete cards. A follow-up would pull a larger
-   model (70 B+ quantized) on matt-strix and see the Strix-only
-   performance ceiling.
-4. **Contention behavior.** The V100 finding generalizes — whenever
-   the homelab is running coresident AI workloads, Gemma 4 inference
-   falls off a cliff. A "contention-aware routing" decision (don't
-   send latency-sensitive Ollama traffic to a card with SDXL running)
-   may be worth building into the mort-bot / openwebui gateway.
 
 ---
 
@@ -225,15 +165,10 @@ All per-run JSON traces are under `scripts/gpu-bakeoff/runs/`:
 runs/
 ├── steel141/
 │   ├── gemma4-26b/{short,long}.json
-│   ├── gemma4-31b/{short,long}.json
+│   └── gemma4-31b/{short,long}.json
-│   └── gemma4-26b-q8/{short,long}.json    # skipped — model not on host
-├── pve197/
-│   ├── gemma4-26b/{short,long}.json        # ⚠ degraded, see caveat
-│   └── gemma4-31b/{short,long}.json        # ⚠ degraded, see caveat
 └── matt-strix/
     ├── gemma4-26b/{short,long}.json
-    ├── gemma4-31b/{short,long}.json
+    └── gemma4-31b/{short,long}.json
-    └── gemma4-26b-q8/{short,long}.json    # skipped — model not on host
 ```
 
 Each JSON contains the warmup call and all 3 measurement calls with

scripts/gpu-bakeoff/runs/pve197/gemma4-26b/long.json

@@ -1,81 +0,0 @@
-{
-  "host": "pve197",
-  "gpu": "Tesla V100-PCIE-32GB",
-  "vram_gb": 32,
-  "model_alias": "gemma4:26b",
-  "model_tag": "gemma4:26b",
-  "prompt_key": "long",
-  "prompt_chars": 1614,
-  "num_predict": 256,
-  "num_ctx": 4096,
-  "runs": [
-    {
-      "prompt_tokens": 318,
-      "prompt_eval_ms": 118.0,
-      "prefill_tok_per_s": 2695.59,
-      "output_tokens": 256,
-      "eval_ms": 32720.5,
-      "decode_tok_per_s": 7.82,
-      "load_ms": 475.8,
-      "total_ms": 33548.1,
-      "harness_wall_s": 33.555,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 318,
-      "prompt_eval_ms": 118.3,
-      "prefill_tok_per_s": 2689.01,
-      "output_tokens": 256,
-      "eval_ms": 31273.0,
-      "decode_tok_per_s": 8.19,
-      "load_ms": 492.5,
-      "total_ms": 32116.6,
-      "harness_wall_s": 32.123,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 318,
-      "prompt_eval_ms": 117.3,
-      "prefill_tok_per_s": 2711.41,
-      "output_tokens": 256,
-      "eval_ms": 33434.9,
-      "decode_tok_per_s": 7.66,
-      "load_ms": 496.0,
-      "total_ms": 34298.7,
-      "harness_wall_s": 34.305,
-      "done_reason": "length"
-    }
-  ],
-  "warmup": {
-    "prompt_tokens": 318,
-    "prompt_eval_ms": 3562.7,
-    "prefill_tok_per_s": 89.26,
-    "output_tokens": 256,
-    "eval_ms": 32215.7,
-    "decode_tok_per_s": 7.95,
-    "load_ms": 491.7,
-    "total_ms": 36521.3,
-    "harness_wall_s": 36.529,
-    "done_reason": "length"
-  },
-  "summary": {
-    "prefill_tok_per_s": {
-      "min": 2689.01,
-      "median": 2695.59,
-      "max": 2711.41,
-      "n": 3
-    },
-    "decode_tok_per_s": {
-      "min": 7.66,
-      "median": 7.82,
-      "max": 8.19,
-      "n": 3
-    },
-    "total_ms": {
-      "min": 32116.6,
-      "median": 33548.1,
-      "max": 34298.7,
-      "n": 3
-    }
-  }
-}

scripts/gpu-bakeoff/runs/pve197/gemma4-26b/short.json

@@ -1,81 +0,0 @@
-{
-  "host": "pve197",
-  "gpu": "Tesla V100-PCIE-32GB",
-  "vram_gb": 32,
-  "model_alias": "gemma4:26b",
-  "model_tag": "gemma4:26b",
-  "prompt_key": "short",
-  "prompt_chars": 78,
-  "num_predict": 256,
-  "num_ctx": 4096,
-  "runs": [
-    {
-      "prompt_tokens": 27,
-      "prompt_eval_ms": 112.5,
-      "prefill_tok_per_s": 240.05,
-      "output_tokens": 256,
-      "eval_ms": 30919.5,
-      "decode_tok_per_s": 8.28,
-      "load_ms": 531.1,
-      "total_ms": 31828.4,
-      "harness_wall_s": 31.832,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 27,
-      "prompt_eval_ms": 113.6,
-      "prefill_tok_per_s": 237.6,
-      "output_tokens": 256,
-      "eval_ms": 30399.9,
-      "decode_tok_per_s": 8.42,
-      "load_ms": 479.4,
-      "total_ms": 31242.1,
-      "harness_wall_s": 31.246,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 27,
-      "prompt_eval_ms": 111.0,
-      "prefill_tok_per_s": 243.16,
-      "output_tokens": 256,
-      "eval_ms": 30712.9,
-      "decode_tok_per_s": 8.34,
-      "load_ms": 483.2,
-      "total_ms": 31552.8,
-      "harness_wall_s": 31.557,
-      "done_reason": "length"
-    }
-  ],
-  "warmup": {
-    "prompt_tokens": 27,
-    "prompt_eval_ms": 843.7,
-    "prefill_tok_per_s": 32.0,
-    "output_tokens": 256,
-    "eval_ms": 30499.4,
-    "decode_tok_per_s": 8.39,
-    "load_ms": 5877.7,
-    "total_ms": 37664.4,
-    "harness_wall_s": 37.668,
-    "done_reason": "length"
-  },
-  "summary": {
-    "prefill_tok_per_s": {
-      "min": 237.6,
-      "median": 240.05,
-      "max": 243.16,
-      "n": 3
-    },
-    "decode_tok_per_s": {
-      "min": 8.28,
-      "median": 8.34,
-      "max": 8.42,
-      "n": 3
-    },
-    "total_ms": {
-      "min": 31242.1,
-      "median": 31552.8,
-      "max": 31828.4,
-      "n": 3
-    }
-  }
-}

scripts/gpu-bakeoff/runs/pve197/gemma4-31b/long.json

@@ -1,81 +0,0 @@
-{
-  "host": "pve197",
-  "gpu": "Tesla V100-PCIE-32GB",
-  "vram_gb": 32,
-  "model_alias": "gemma4:31b",
-  "model_tag": "gemma4:31b-it-q4_K_M",
-  "prompt_key": "long",
-  "prompt_chars": 1614,
-  "num_predict": 256,
-  "num_ctx": 4096,
-  "runs": [
-    {
-      "prompt_tokens": 318,
-      "prompt_eval_ms": 728.7,
-      "prefill_tok_per_s": 436.37,
-      "output_tokens": 256,
-      "eval_ms": 163511.0,
-      "decode_tok_per_s": 1.57,
-      "load_ms": 495.0,
-      "total_ms": 164970.4,
-      "harness_wall_s": 164.977,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 318,
-      "prompt_eval_ms": 682.8,
-      "prefill_tok_per_s": 465.71,
-      "output_tokens": 256,
-      "eval_ms": 168727.1,
-      "decode_tok_per_s": 1.52,
-      "load_ms": 545.3,
-      "total_ms": 170207.4,
-      "harness_wall_s": 170.214,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 318,
-      "prompt_eval_ms": 950.0,
-      "prefill_tok_per_s": 334.75,
-      "output_tokens": 256,
-      "eval_ms": 163102.9,
-      "decode_tok_per_s": 1.57,
-      "load_ms": 507.9,
-      "total_ms": 164801.8,
-      "harness_wall_s": 164.809,
-      "done_reason": "length"
-    }
-  ],
-  "warmup": {
-    "prompt_tokens": 318,
-    "prompt_eval_ms": 3883.3,
-    "prefill_tok_per_s": 81.89,
-    "output_tokens": 256,
-    "eval_ms": 172199.4,
-    "decode_tok_per_s": 1.49,
-    "load_ms": 528.0,
-    "total_ms": 176864.8,
-    "harness_wall_s": 176.871,
-    "done_reason": "length"
-  },
-  "summary": {
-    "prefill_tok_per_s": {
-      "min": 334.75,
-      "median": 436.37,
-      "max": 465.71,
-      "n": 3
-    },
-    "decode_tok_per_s": {
-      "min": 1.52,
-      "median": 1.57,
-      "max": 1.57,
-      "n": 3
-    },
-    "total_ms": {
-      "min": 164801.8,
-      "median": 164970.4,
-      "max": 170207.4,
-      "n": 3
-    }
-  }
-}

scripts/gpu-bakeoff/runs/pve197/gemma4-31b/short.json

@@ -1,81 +0,0 @@
-{
-  "host": "pve197",
-  "gpu": "Tesla V100-PCIE-32GB",
-  "vram_gb": 32,
-  "model_alias": "gemma4:31b",
-  "model_tag": "gemma4:31b-it-q4_K_M",
-  "prompt_key": "short",
-  "prompt_chars": 78,
-  "num_predict": 256,
-  "num_ctx": 4096,
-  "runs": [
-    {
-      "prompt_tokens": 27,
-      "prompt_eval_ms": 665.6,
-      "prefill_tok_per_s": 40.56,
-      "output_tokens": 256,
-      "eval_ms": 164631.1,
-      "decode_tok_per_s": 1.55,
-      "load_ms": 512.6,
-      "total_ms": 166062.7,
-      "harness_wall_s": 166.067,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 27,
-      "prompt_eval_ms": 660.3,
-      "prefill_tok_per_s": 40.89,
-      "output_tokens": 256,
-      "eval_ms": 159594.3,
-      "decode_tok_per_s": 1.6,
-      "load_ms": 523.6,
-      "total_ms": 161012.3,
-      "harness_wall_s": 161.016,
-      "done_reason": "length"
-    },
-    {
-      "prompt_tokens": 27,
-      "prompt_eval_ms": 887.8,
-      "prefill_tok_per_s": 30.41,
-      "output_tokens": 256,
-      "eval_ms": 167584.3,
-      "decode_tok_per_s": 1.53,
-      "load_ms": 486.8,
-      "total_ms": 169188.9,
-      "harness_wall_s": 169.194,
-      "done_reason": "length"
-    }
-  ],
-  "warmup": {
-    "prompt_tokens": 27,
-    "prompt_eval_ms": 6642.4,
-    "prefill_tok_per_s": 4.06,
-    "output_tokens": 256,
-    "eval_ms": 173530.1,
-    "decode_tok_per_s": 1.48,
-    "load_ms": 20142.1,
-    "total_ms": 200836.5,
-    "harness_wall_s": 200.841,
-    "done_reason": "length"
-  },
-  "summary": {
-    "prefill_tok_per_s": {
-      "min": 30.41,
-      "median": 40.56,
-      "max": 40.89,
-      "n": 3
-    },
-    "decode_tok_per_s": {
-      "min": 1.53,
-      "median": 1.55,
-      "max": 1.6,
-      "n": 3
-    },
-    "total_ms": {
-      "min": 161012.3,
-      "median": 166062.7,
-      "max": 169188.9,
-      "n": 3
-    }
-  }
-}