Back to models
Intelligence Index
Reasoning setting
16.7
Estimated · Artificial Analysis v4.3.2- API price from
- $0.06 in / $0.33 out / 1M tokOpenRouter · DekaLLM · BF16
- Context window
- 256K tok
Performance profile
ReasoningRank #54 of 107
79.2%
GPQA DiamondCodingRank #64 of 94
40.0%
SciCodeCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)ReasoningEstimated
- Intelligence Index
- 16.7
Pricing & access
USD per 1M tokens
- Input
- $0.06
- Output
- $0.33
- Cached input
- $0.04
Run locally
GGUF
Context
Estimated memory
~19.4 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.
24 GiB RAMwithout GPU offload
Memory budgetOne text chat
- Weights
- 15.6 GiB
- Context cache
- 1.7 GiB16-bit cache
- App allowance
- 2 GiB
- Download
- 16.8 GB+1.2 GB for images (opens in a new tab)
- Disk space
- ~25 GBIncludes image file
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/gemma-4-26B-A4B-it-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/gemma-4-26B-A4B-it-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.
Images need extra memoryvLLM setup (opens in a new tab)
Benchmarks
Full leaderboardSource (opens in a new tab)19.3%, rank 67 of 12640.0%, rank 64 of 9465.7%, rank 71 of 125566 Elo, rank 72 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 64o3Reasoning20.1%
- 65GPT-5.5 Instant (June 2026)Reasoning19.9%
- 66gpt-oss-120bHigh19.6%
- 67Gemma 4 26B A4BReasoning19.3%
- 68Gemini 3.5 Flash-LiteHigh18.8%
- 69Quasar 438BMax18.7%
- 70K-EXAONE 2.0 0803Reasoning18.6%
Peers use their best measured result on this benchmark.