Granite 4.0 H Small
Granite 4.0 H SmallRankingin non-thinking mode?
Alternatives?
CheaperSolar Mini 4×4-5%$0.37
BetterGPT-6 Lunalow×3.6+116%$0.005Function calling only with none · Chat Completions+3
OpenQwen3.8 27Bxhigh×5.6+934%$1.01max_tokens range · QwenCloud+4CheaperQwen3.5 4BthinkingOpen×2.2-35%$0.03 / $0.15
CheaperNemotron 3.5 LightningthinkingOpen×2.1-47%$0.079Memory (4-bit): 19 GB → 20 GBSolar Mini 4×4-5%$0.37Qwen3.5 4BthinkingOpen×2.2-35%$0.03 / $0.15Nemotron 3.5 LightningthinkingOpen×2.1-47%$0.079Memory (4-bit): 19 GB → 20 GBGPT OSS 120BhighOpen+92%-35%$0.092Memory (4-bit): 19 GB → 70 GBGPT OSS 20BlowOpen+65%-61%$0.018 / $0.09GPT-6 Lunalow×3.6+116%$0.005Function calling only with none · Chat Completions+3Granite 4.2 3BthinkingOpen+50%-43%$0.006
Gemma 4 E4BthinkingOpen+47%-57%$0.008GPT-5.6 Lunalow×3.5+386%$0.01GPT OSS 20BhighOpen+48%-61%$0.011Qwen3.8 27BxhighOpen×5.6+934%$1.01max_tokens range · QwenCloud+4IK2 Horizon MoVA 36B A4BthinkingOpen×4.2+1,792%$1 / $4Memory (4-bit): 19 GB → 22 GBQwen 3.5 27BthinkingOpen×3.8+792%$0.30 / $2.40AG9v3 39A5BOpen×3.6——Memory (4-bit): 19 GB → 23 GBQwen3.6 27BthinkingOpen×3.5+1,359%$0.62Granite 4.2 30BthinkingOpen×2.1—$0.072Granite 4.2 8BthinkingOpen+83%—$0.024Granite 4.2 3BthinkingOpen+50%—$0.006Granite 4.1 30BOpen+23%—$0.10 / $0.25Granite 4.1 8Bnon-thinkingOpensame——Granite 4.1 3BOpensame——Granite 4.0 H 1BOpensame——Granite 4.0 Micronon-thinkingOpensame—$0.017 / $0.11All 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 Jamba 1.7 Large?›
On AA Intelligence Index 4.3.2, Granite 4.0 H Small scores 6 vs 6.1 — 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?›
Solar Mini 4 (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).