Back to models
Intelligence Index
Standard setting
6.3
Estimated · Artificial Analysis v4.3.2- Context window
- 128K tok
Performance profile
ReasoningRank #103 of 107
33.1%
GPQA DiamondCapabilities
Context window
Modalities
Measured setting
Reasoning trade-offs
Source (opens in a new tab)StandardEstimated
- Intelligence Index
- 6.3
Pricing & access
No API offering listed in our tracked sources.
Run locally
GGUF
Context
Estimated memory
~5.3 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
- 2.3 GiB
- Context cache
- 1 GiB16-bit cache
- App allowance
- 2 GiB
- Download
- 2.5 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/Phi-4-mini-instruct-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/Phi-4-mini-instruct-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)4.5%, rank 118 of 12615.3%, rank 114 of 125-408 Elo, rank 100 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 114Nova MicroStandard4.6%
- 114Ministral 3 14BStandard4.6%
- 117G9v3-3BReasoning4.5%
- 118Phi-4 Mini InstructStandard4.5%
- 119Reka Flash 3Reasoning4.4%
- 120Ministral 3 8BStandard4.3%
- 121Nova PremierStandard4.2%
Peers use their best measured result on this benchmark.