Granite 4.0 Micro
IBM · released Sep 16, 2025 · ibm-granite/granite-4.0-h-micro
- Type
- Open weightsApache License 2.0
- Params
- 3.2B
- Context
- 131K
about 98K words of context
Our take
Written Sep 4, 2026Granite 4.0 Micro is a compact text-only model from IBM with a permissive Apache licence and a 131,000-token request limit. It is built for lightweight text tasks where low cost and open licensing matter more than measured quality scores.
Pick this when you need a permissive open licence for a small text model, or for cost-sensitive text tasks at the cheapest tier. Use it on Cloudflare edge where 35 tokens per second is enough throughput. Skip it if you need benchmark-verified quality, multimodal input, or guaranteed speed on every host.
The case for it
- Apache 2.0 licence allows commercial use, modification and redistribution without restriction.
- Very low inference cost, with the same rate across both tracked providers.
- 131,000-token request limit is substantial for a 3.2-billion-parameter model.
The case against it
- No benchmark scores in our data, so chat, reasoning, coding and other task performance is unverified.
- Throughput is undisclosed on one of two offers; only Cloudflare's 35 tokens per second is known.
- Whether the architecture is dense or mixture-of-experts is unverified in our data.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 19.4 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 27.4 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 2.6 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.017 in / $0.11 out
- Context served
- 131K
- Throughput
- ~29 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.017 / $0.11checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| Cloudflare Workers AIThrough OpenRouter | $0.017 / $0.11checked 4 hours ago | 131K118K max reply | 29 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✗ |
| Cloudflare Workers AIThrough OpenRouter | ✗ | ✓ | ✗ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- ibm-granite/granite-4.0-h-micro
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- ibm-granite-granite-4-0-micro