Tool Gauntlet — tool-gauntlet-v1
Code Generation Tool Calling RAG / Q&A Reasoning / Math | About

The Gauntlet

Six escalating tests, run identically across every model. Find what actually holds up on your hardware — organized by VRAM tier, not marketing size class.

Sub-4GB

6 models tested
1.8 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 176.2 tok · 3.45s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 202.0 tok · 1.34s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 226.8 tok · 1.48s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 376.0 tok · 2.24s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 431.0 tok · 2.86s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 417.6 tok · 2.45s
30/30
3.4 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 230.0 tok · 4.62s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 195.8 tok · 1.75s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 217.0 tok · 1.87s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 372.6 tok · 3.03s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 359.2 tok · 3.27s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 369.6 tok · 3.0s
30/30
granite4:3b Champion
2.9 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 20.0 tok · 0.56s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 8.0 tok · 0.13s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 28.0 tok · 0.23s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 44.0 tok · 0.32s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 37.0 tok · 0.39s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 71.0 tok · 0.45s
30/30
3.1 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 17.0 tok · 0.59s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 0/5 · 18.0 tok · 0.2s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 18.0 tok · 0.22s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 0/5 · 41.0 tok · 0.32s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 0/5 · 98.0 tok · 0.68s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 0/5 · 48.0 tok · 0.34s
10/30
3.7 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 0/5 · 12.0 tok · 0.69s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 84.0 tok · 0.55s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 0/5 · 832.2 tok · 4.2s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 0/5 · 269.2 tok · 1.44s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 0/5 · 105.0 tok · 0.65s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 0/5 · 201.6 tok · 1.11s
5/30
2.7 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 0/5 · 626.4 tok · 3.18s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 485.4 tok · 2.21s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 0/5 · 827.6 tok · 3.63s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 0/5 · 879.6 tok · 3.88s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 0/5 · 408.6 tok · 1.88s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 0/5 · 647.8 tok · 2.87s
5/30

4-8GB

4 models tested
qwen3.5:9b Champion
5.7 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 85.0 tok · 1.02s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 93.0 tok · 1.02s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 87.0 tok · 0.99s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 205.0 tok · 1.94s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 146.0 tok · 1.71s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 177.0 tok · 1.72s
30/30
6.3 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 94.0 tok · 1.53s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 206.8 tok · 1.61s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 104.4 tok · 0.87s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 341.2 tok · 2.59s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 242.6 tok · 2.01s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 270.6 tok · 2.08s
30/30
5.6 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 21.0 tok · 1.43s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 0/5 · 126.0 tok · 0.84s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 4/5 · 140.6 tok · 0.94s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 88.0 tok · 0.59s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 0/5 · 112.2 tok · 0.75s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 92.0 tok · 0.62s
19/30
5.1 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 0/5 · 17.0 tok · 0.55s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 18.0 tok · 0.23s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 0/5 · 18.0 tok · 0.24s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 0/5 · 56.0 tok · 0.5s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 0/5 · 32.0 tok · 0.33s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 0/5 · 61.0 tok · 0.55s
5/30

8-12GB

4 models tested
8.0 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 62.0 tok · 2.07s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 45.0 tok · 0.82s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 97.0 tok · 1.47s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 245.6 tok · 3.19s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 160.6 tok · 2.53s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 162.8 tok · 2.2s
30/30
8.4 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 79.0 tok · 3.48s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 42.0 tok · 0.87s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 90.0 tok · 1.6s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 265.0 tok · 4.02s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 154.0 tok · 2.78s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 161.2 tok · 2.52s
30/30
10 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 111.0 tok · 3.44s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 224.2 tok · 2.79s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 131.0 tok · 1.71s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 197.0 tok · 2.5s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 260.6 tok · 3.42s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 303.0 tok · 3.79s
30/30
10 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 0/5 · 34.0 tok · 2.58s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 12.0 tok · 0.26s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 0/5 · 34.0 tok · 0.54s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 0/5 · 804.0 tok · 10.2s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 0/5 · 34.0 tok · 0.55s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 0/5 · 962.8 tok · 12.18s
5/30

12GB+

3 models tested
gemma4:26b Champion
17 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 131.0 tok · 3.72s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 45.0 tok · 0.65s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 122.0 tok · 1.3s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 203.6 tok · 1.9s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 183.2 tok · 2.08s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 194.0 tok · 1.83s
30/30
22 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 92.0 tok · 4.9s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 122.0 tok · 3.2s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 147.0 tok · 3.85s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 245.6 tok · 6.35s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 5/5 · 338.0 tok · 8.96s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 273.4 tok · 7.08s
30/30
15 GB measured VRAM
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 1 — floor: 5/5 · 13.0 tok · 2.34s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 2 — restraint: 5/5 · 8.0 tok · 0.3s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 3 — selection: 5/5 · 11.0 tok · 0.36s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 4 — extraction: 5/5 · 41.0 tok · 0.89s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 5 — chaining: 0/5 · 32.0 tok · 0.94s
[This tool call rendered an interactive widget in the chat. The user can already see the result — do not repeat it in text or with another visualization tool.] Tier 6 — strict schema: 5/5 · 46.0 tok · 1.0s
25/30