Back to models
Intelligence Index
Standard setting
5.1
Estimated · Artificial Analysis v4.3.2- API price from
- ≈ $0.02 in / ≈ $0.11 out / 1M tokOpenRouter · Cloudflare
- Context window
- 128K tok
Performance profile
ReasoningRank #102 of 107
33.6%
GPQA DiamondCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)StandardEstimated
- Intelligence Index
- 5.1
Pricing & access
USD per 1M tokens
- Input
- $0.017
- Output
- $0.112
Run locally
GGUF
Context
Estimated memory
~4.6 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.
16 GiB RAMwithout GPU offload
Memory budgetOne text chat
- Weights
- 2 GiB
- Context cache
- 0.6 GiB16-bit cache
- App allowance
- 2 GiB
- Download
- 2.1 GB
- Disk space
- ~8 GB
Get GGUF (opens in a new tab)
Set up in Ollama · Q4_K_M · 8K context
Save the following as Modelfile. The context matches the estimate above.
FROM hf.co/lmstudio-community/granite-4.0-micro-GGUF:Q4_K_M 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 lmstudio-community/granite-4.0-micro-GGUF, choose Q4_K_M, 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)5.0%, rank 109 of 1267.0%, rank 118 of 125
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 106Ministral 3 3BStandard5.4%
- 106K2 Horizon 0.9BReasoning5.4%
- 108Tiny Aya GlobalStandard5.2%
- 109Granite 4.0 MicroStandard5.0%
- 110Phi-4 Multimodal InstructStandard5.0%
- 111Llama 4 MaverickStandard4.9%
- 112NVIDIA Nemotron Nano 9B V2Reasoning4.9%
Peers use their best measured result on this benchmark.