Granite 4.2 3B
Granite 4.2 3BRankingin thinking mode?
Alternatives?
CheaperGPT-6 Lunalow×2.4-25%$0.005Function calling only with none · Chat Completions+3IOpenK2 Horizon 7Bthinking×2.3+900%$0.30 / $1.20Memory (4-bit): 1.8 GB → 4.5 GBCheaperGPT OSS 20BlowOpensame-31%$0.018 / $0.09Memory (4-bit): 1.8 GB → 13 GB
CheaperGemma 4 E4Bnon-thinkingOpen-18%-24%$0.02 / $0.10Memory (4-bit): 1.8 GB → 4 GB
CheaperQwen3.5 2BthinkingOpen-23%-24%$0.02 / $0.10GPT-6 Lunalow×2.4-25%$0.005Function calling only with none · Chat Completions+3GPT OSS 20BlowOpensame-31%$0.018 / $0.09Memory (4-bit): 1.8 GB → 13 GBGemma 4 E4Bnon-thinkingOpen-18%-24%$0.02 / $0.10Memory (4-bit): 1.8 GB → 4 GBQwen3.5 2BthinkingOpen-23%-24%$0.02 / $0.10Qwen3.5 0.8BthinkingOpen-32%-62%$0.01 / $0.05GPT-6 Lunalow×2.4-25%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow×2.3+64%$0.01
Mistral Small 4thinkingOpen+24%+151%$0.015Memory (4-bit): 1.8 GB → 72 GB
MiMo v2.5thinkingOpen×2.4+219%$0.019Memory (4-bit): 1.8 GB → 186 GBGranite 4.2 8BthinkingOpen+22%+294%$0.024Memory (4-bit): 1.8 GB → 4.4 GBGemma 4 12BthinkingOpen+57%+186%$0.10 / $0.30Memory (4-bit): 1.8 GB → 6 GBQwen 3.5 9Bnon-thinkingOpen+46%+76%$0.08 / $0.13Memory (4-bit): 1.8 GB → 4.8 GBQwen3.5 4BthinkingOpen+45%+14%$0.03 / $0.15Memory (4-bit): 1.8 GB → 2.3 GBGranite 4.2 30BthinkingOpen+40%+1,097%$0.072Memory (4-bit): 1.8 GB → 18 GBGranite 4.2 8BthinkingOpen+22%+294%$0.024Memory (4-bit): 1.8 GB → 4.4 GBGranite 4.1 30BOpen-18%—$0.10 / $0.25Memory (4-bit): 1.8 GB → 17 GBGranite 4.1 8Bnon-thinkingOpen-27%——Memory (4-bit): 1.8 GB → 4.4 GBGranite 4.0 H Smallnon-thinkingOpen-33%—$0.05 / $0.22Memory (4-bit): 1.8 GB → 19 GBGranite 4.1 3BOpen-35%——Granite 4.0 H 1BOpen-43%——Granite 4.0 Micronon-thinkingOpen-44%—$0.017 / $0.11All IBM models →Run it yourself
estimateHistory
2 versionsBenchmarks
all categoriesFAQ
How much does Granite 4.2 3B cost?›
$0.03 per 1M input tokens and $0.12 per 1M output tokens (cheapest host: DeepInfra). A typical benchmark task costs about $0.006 at default effort.
Is Granite 4.2 3B free to use?›
There is no free API; the cheapest paid price is $0.03 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Granite 4.2 3B, and what is it best at?›
#230 of 334 in Chat & Knowledge, #75 of 132 in Coding, #124 of 133 in Agents & Tool Use, #174 of 195 in Writing & Language, #130 of 133 in Vision & Documents.
Is Granite 4.2 3B better than Granite 4.1 3B?›
On AA Intelligence Index 4.3.2, Granite 4.2 3B scores 9.1 vs 5.9 — higher.
How can I use Granite 4.2 3B?›
Through the API of DeepInfra.
What is the context window of Granite 4.2 3B?›
128K tokens.
When was Granite 4.2 3B released? Is there a newer version?›
Released 2026-08-25. It is the current version in its line.
Is Granite 4.2 3B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Granite 4.2 3B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Granite 4.2 3B read images?›
No, it accepts text only.
What is Granite 4.2 3B?›
Granite 4.2 3B is an open-weights language model from IBM, released Aug 2026, the successor to Granite 4.1 3B.
What are the best alternatives to Granite 4.2 3B?›
GPT-6 Luna (cheaper), K2 Horizon 7B (open weights).