AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#202

Inkling 2 Mini (local Q4)

Thinkingmachines Release: 2026-11-20 Tested on: 2026-11-22 16:20 thinkingmachines/inkling-2-mini-local::low
26.4B total (3.4B active)MoEOpen source
(low) (minimal)

Summary

Inkling 2 Mini (local Q4) scores 7.6 on AI BENCHY and ranks #202. It has 9.7 reliability, a 66.7% pass rate, ~$0.292 total cost, and 153.99s average response time.

What makes Inkling 2 Mini (local Q4) unique: It stands out most in Domain specific, where it ranks #1, while Coding is its weakest area at #15.

Model facts

Researched on 2026-11-22

Reported
Parameters
26.4B total (3.4B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0

Same weights as Inkling 2 Mini, quantized by Unsloth to UD-Q4_K_XL GGUF and run locally through llama.cpp b12631. Multimodal looped sparse MoE: 8 of 128 experts per token, middle layers run three times (about 5.4B effective active parameters). Public Apache-2.0 weights with vLLM, SGLang and transformers instructions; use is also subject to the Thinking Machines Model Acceptable Use Policy. Training code and data are not published. Released 2026-11-20.

Score

7.6

Consistency

9.6

Total Cost (Current Price)

~$0.292

Total Output Tokens

129,600

Total Input Tokens

312,366

Estimated benchmark electricity cost

~$0.292

Tests Correct

Wrong Tests: 8

Attempt pass rate: 66.7%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

153.99s

Response Time (max): 1963.67s

Response Time (total): 3541.85s

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

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 10.0 10.0
Coding 5.3 7.2
Combined 6.5 10.0
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 5.5 10.0
Instructions following 9.8 10.0
Puzzle Solving 5.8 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models