Granite 4.0 H Small
Granite 4.0 H SmallRankingin non-thinking mode?
Alternatives?
CheaperGemma 3 12BunstatedOpenwins 63%-32%$0.05 / $0.10
BetterGPT-5 Minihighwins 61%+643%$0.053OpenGemma 4 31Bunstatedwins 73%+73%$0.10 / $0.34CheaperGPT OSS 120BunstatedOpenwins 55%-35%$0.03 / $0.15Memory (4-bit): 19 GB → 70 GBCheaperGemma 3 4BunstatedOpenwins 55%-54%$0.04 / $0.05Gemma 3 12BunstatedOpenwins 63%-32%$0.05 / $0.10GPT OSS 120BunstatedOpenwins 55%-35%$0.03 / $0.15Memory (4-bit): 19 GB → 70 GBGemma 3 4BunstatedOpenwins 55%-54%$0.04 / $0.05Gemma 2 9B ItOpenwins 52%-59%$0.03 / $0.06Context: 128K → 8KGPT OSS 20BunstatedOpensame-61%$0.018 / $0.09GPT-5 Minihighwins 61%+643%$0.053GPT-6 Lunamaxwins 72%+116%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 72%+386%$0.085GPT-5.6 Terraxhighwins 74%+4,765%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 78%+4,224%$0.72Remove unsupported parameters+5Gemma 4 31BunstatedOpenwins 73%+73%$0.10 / $0.34Gemma 4 26B A4BunstatedOpenwins 71%+184%$0.15 / $0.60
Qwen3.8 27BunstatedOpenwins 67%+934%$0.42 / $2.55max_tokens range · QwenCloud+4
Muse Glimmer 30BunstatedOpenwins 67%+441%$0.30 / $1.10Qwen 3.5 27BunstatedOpenwins 66%+792%$0.30 / $2.40Granite 4.2 30BunstatedOpenwins 53%—$0.16 / $0.65Granite 4.1 8BunstatedOpenwins 53%——Granite 4.2 3BunstatedOpenwins 45%—$0.03 / $0.12Granite 4.2 8BunstatedOpenwins 44%—$0.06 / $0.25Granite 4.1 30BOpenn/a—$0.10 / $0.25Granite 4.1 3BOpenn/a——Granite 4.0 350Mnon-thinkingOpenn/a——Context: 128K → 33KGranite 4.0 H 350MOpenn/a——Context: 128K → 33KAll IBM models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Granite 4.0 H Small cost?›
$0.05 per 1M input tokens and $0.22 per 1M output tokens.
Is Granite 4.0 H Small free to use?›
There is no free API; the cheapest paid price is $0.05 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Granite 4.0 H Small, and what is it best at?›
#313 of 334 in Chat & Knowledge, #181 of 239 in Coding, #202 of 242 in Agents & Tool Use, #162 of 195 in Writing & Language.
Is Granite 4.0 H Small better than GPT-5 Nano?›
On Arena Text · creative writing, Granite 4.0 H Small scores 1,243 vs 1,246 — about the same.
How can I use Granite 4.0 H Small?›
Through the API of IBM.
What is the context window of Granite 4.0 H Small?›
128K tokens.
When was Granite 4.0 H Small released? Is there a newer version?›
Released 2025-09-22. It is the current version in its line.
Is Granite 4.0 H Small open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Granite 4.0 H Small locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Granite 4.0 H Small read images?›
No, it accepts text only.
What is Granite 4.0 H Small?›
Granite 4.0 H Small is an open-weights language model from IBM, released Sep 2025.
What are the best alternatives to Granite 4.0 H Small?›
Gemma 3 12B (cheaper), GPT-5 Mini (better), Gemma 4 31B (open weights).