Navigate
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Inkling 2 Mini (local Q4) — low vs minimal

minimal leads on average score with 8.7 vs 7.6. minimal has the lower benchmark cost at ~$0.206 vs ~$0.292. minimal is faster at 108.28s vs 153.99s, with pass rates of 66.7% vs 73.9%.

Last updated at: 2026-11-22

Compared models

Rank
#202
Total Output Tokens
129,600
Response Time (avg)
153.99s
Total Cost
~$0.292
Rank
#108
Total Output Tokens
219,084
Response Time (avg)
108.28s
Total Cost
~$0.206
Recommended model minimal

It has the strongest score in this comparison (8.7) and the best overall balance of cost and response time across 2 models.

Detailed comparison

Metric Inkling 2 Mini (local Q4) Inkling 2 Mini (local Q4) low Release: 2026-11-20 Inkling 2 Mini (local Q4) Inkling 2 Mini (local Q4) minimal Release: 2026-11-20
Score 7.6 8.7
Rank #202 #108
Reliability 9.7 9.8
Consistency 9.6 10.0
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 66.7% 73.9%
Flaky tests 1 0
Total Runs 69 69
Cost per result ~1.946 ~1.207
Total Cost ~$0.292 ~$0.206
Input Price N/A N/A
Output Price N/A N/A
Cache Read Price N/A N/A
Cache Write Price N/A N/A
Total Input Tokens 312,366 309,808
Output Tokens 1,631 1,579
Reasoning Tokens 127,969 217,505
Response Time (avg) 153.99s 108.28s
Response Time (max) 1963.67s 1322.88s
Response Time (total) 3541.85s 2490.37s
Parameters 26.4B total (3.4B active) 26.4B total (3.4B active)
Availability Open source Open source

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#202 Thinking Machines: Inkling 2 Mini (local Q4)

low
Cost
~$0.003
Time
85.5s
Tokens
2,977 tok

#108 Thinking Machines: Inkling 2 Mini (local Q4)

minimal
Cost
~$0.002
Time
67.8s
Tokens
2,348 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Inkling 2 Mini (local Q4) 5.3 7.2 44.4% 1 831.97s 5,668 524 34,490
Inkling 2 Mini (local Q4) 10.0 10.0 100.0% 0 225.36s 8,814 512 47,862

Switch Comparison Pair

Qwen4 MaxlowvsInkling 2 Mini (local Q4)minimalClaude Fable 5.2highvsInkling 2 Mini (local Q4)minimalGPT-6 SollowvsInkling 2 Mini (local Q4)minimalSeed 2.1 TurbomediumvsInkling 2 Mini (local Q4)minimalInkling 2 Mini (local Q4)minimalvsMiMo-V2.6-PromediumQwen3.8 27BhighFree AvailablevsInkling 2 Mini (local Q4)minimalMuse EmberlowvsInkling 2 Mini (local Q4)minimalMuse EmbermaxvsInkling 2 Mini (local Q4)minimalGPT-5.2mediumvsInkling 2 Mini (local Q4)minimalERNIE-Light-DT-1.0highvsInkling 2 Mini (local Q4)minimalDeepSeek V4.1 FlashmaxvsInkling 2 Mini (local Q4)minimalParticle-1xhighvsInkling 2 Mini (local Q4)minimal