Back to models
Intelligence Index
Standard setting
5.9
Estimated · Artificial Analysis v4.3.2- API price from
- $0.07 in / $0.14 out / 1M tokOpenRouter · DeepInfra · BF16
- Context window
- 16K tok
Performance profile
ReasoningRank #86 of 107
57.5%
GPQA DiamondCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)StandardEstimated
- Intelligence Index
- 5.9
Pricing & access
USD per 1M tokens
- Input
- $0.07
- Output
- $0.14
Run locally
GGUF
Context
Estimated memory
~12 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
- 8.4 GiB
- Context cache
- 1.6 GiB16-bit cache
- App allowance
- 2 GiB
- Download
- 9.1 GB
- Disk space
- ~15 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-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-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)3.8%, rank 125 of 1260.0%, rank 121 of 125
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 120Ministral 3 8BStandard4.3%
- 121Nova PremierStandard4.2%
- 122Command AStandard4.0%
- 123Granite 4.0 H SmallStandard3.8%
- 124Llama 4 ScoutStandard3.8%
- 125Phi-4Standard3.8%
- 126Llama 3.3 Instruct 70BStandard3.6%
Peers use their best measured result on this benchmark.