Extra high setting
- API price from
- $0.95 in / $4.05 out / 1M tokOpenRouter · DeepInfra · FP8
- Context window
- 1M tok
Performance profile
Capabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)- Intelligence Index
- 25.0
- Cost / task
- $0.607
- Evaluation time
- 5.2m
Pricing & access
USD per 1M tokens
- Input
- $0.95
- Output
- $4.05
- Cached input
- $0.16
Run locally
~881.5 GiB
RAM + VRAM
Estimate assumptions
One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.
1024 GiB RAMwithout GPU offload
- Weights
- 797.9 GiB
- Context + state
- 3.8 GiB16-bit cache
- App allowance
- 79.8 GiB
- Download
- 856.8 GB19 files · keep together+0.2 GB for images (opens in a new tab)
- Disk space
- ~948 GBIncludes image file
Set up in Ollama · Q8_0 · 8K context
Save the following as Modelfile. The context matches the estimate above.
FROM hf.co/unsloth/inkling-GGUF:Q8_0 PARAMETER num_ctx 8192
Then run these commands in your terminal:
ollama create llmcurrent-local -f Modelfile ollama run llmcurrent-local
Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter unsloth/inkling-GGUF, choose Q8_0, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.
Benchmarks
Full leaderboardSource (opens in a new tab)Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 45Hy3Reasoning33.5%
- 46Inkling SmallReasoning33.3%
- 47K2 Horizon 375B A23BReasoning32.0%
- 48InklingExtra high31.9%
- 49Nemotron 3.5 Super VLReasoning30.7%
- 50A.X-K2Reasoning29.6%
- 51Solar Pro 4Reasoning29.2%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherQwen3.7 PlusReasoning
- Intelligence Index
- 25.2+0.2
- Cost / task
- $0.217−64%
- Higher score, lower costMiMo-V2.6-ProReasoning
- Intelligence Index
- 46.3+21.3
- Cost / task
- $0.133−78%
- More from Thinking MachinesInkling SmallReasoning
- Intelligence Index
- 25.7+0.7
- Cost / task
- $0.089−85%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.