Apertus 8B vs Granite-4.0-H-Small vs Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B comes out ahead, 64 to 61 and 54 on our weighted score, and it is the cheaper option too.
Swiss AI
Apertus 8B
54/100- ECI—
- Price$0.10 / $0.20
- Context66K
IBMGranite-4.0-H-Small
61/100- ECI—
- Price$0.064 / $0.265
- Context131K
- Our pick
NVIDIANemotron 3 Nano 30B A3B
64/100- ECI—
- Price$0.06 / $0.24
- Context262K
Nemotron 3 Nano 30B A3B is our pick
Nemotron 3 Nano 30B A3B is the better all-round choice, scoring 64/100 against Granite-4.0-H-Small (61) and Apertus 8B (54). It leads on price and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNemotron 3 Nano 30B A3BNemotron 3 Nano 30B A3B $0.105 · Granite-4.0-H-Small $0.114 · Apertus 8B $0.125 per 1M tokens (3:1 blend)
- Longest contextNemotron 3 Nano 30B A3BNemotron 3 Nano 30B A3B 262,144 · Granite-4.0-H-Small 131,072 · Apertus 8B 65,536 tokens
- Widest inputsSame inputsApertus 8B: Text · Granite-4.0-H-Small: Text · Nemotron 3 Nano 30B A3B: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Apertus 8B | Granite-4.0-H-Small | Nemotron 3 Nano 30B A3B |
|---|---|---|---|---|
| Price | 50% | 89 | 91 | 92 |
| Inputs & features | 30% | 25 | 35 | 35 |
| Context window | 20% | 12 | 25 | 37 |
| Overall | 100% | 54/100 | 61/100 | 64/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Apertus 8BSwiss AI | Granite-4.0-H-SmallIBM | Nemotron 3 Nano 30B A3BNVIDIA |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.10 | $0.064 | $0.06 (best) |
| Output | $0.20 (best) | $0.265 | $0.24 |
| Cached input | — | — | — |
| Blended (3:1) | $0.125 | $0.114 | $0.105 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 1 providers | Official watsonx.ai API | Median of 15 providers |
| Limits | |||
| Context window | 65,536 tokens | 131,072 tokens | 262,144 tokens (best) |
| Max output | 8,192 tokens | 131,072 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenApache-2.0 | Open | Open |
| API model ID | — | ibm/granite-4-h-small | — |
| API providers | 1 | 1 | 16 (best) |
| Released | Sep 2, 2025 | Oct 2, 2025 | Dec 15, 2025 |
| Knowledge cutoff | Sep 2025 | — | Jun 25, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Apertus 8B$1.40
- Granite-4.0-H-Small$1.17
- Nemotron 3 Nano 30B A3B$1.08
Which should you choose?
Which is better: Apertus 8B, Granite-4.0-H-Small or Nemotron 3 Nano 30B A3B?
Nemotron 3 Nano 30B A3B is the better all-round choice, scoring 64/100 against Granite-4.0-H-Small (61) and Apertus 8B (54). It leads on price and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Apertus 8B, Granite-4.0-H-Small or Nemotron 3 Nano 30B A3B?
Nemotron 3 Nano 30B A3B is cheaper at $0.06 input / $0.24 output per million tokens (median across 15 API providers). Granite-4.0-H-Small costs $0.064 input / $0.265 output per million tokens (official watsonx.ai API price); Apertus 8B costs $0.10 input / $0.20 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.105 per million tokens for Nemotron 3 Nano 30B A3B versus $0.114 for Granite-4.0-H-Small (1.1× as much) and $0.125 for Apertus 8B (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Apertus 8B has not been scored yet, Granite-4.0-H-Small has not been scored yet and Nemotron 3 Nano 30B A3B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Apertus 8B, Granite-4.0-H-Small and Nemotron 3 Nano 30B A3B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Nemotron 3 Nano 30B A3B has the largest context window at 262,144 tokens, against 131,072 for Granite-4.0-H-Small and 65,536 for Apertus 8B. Maximum output per response: Apertus 8B up to 8,192, Granite-4.0-H-Small up to 131,072, Nemotron 3 Nano 30B A3B up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Apertus 8B accepts text; Granite-4.0-H-Small accepts text; Nemotron 3 Nano 30B A3B accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (Apache-2.0), so you can self-host them.
Which is newer?
Nemotron 3 Nano 30B A3B is the newest, released Dec 15, 2025. Granite-4.0-H-Small came out Oct 2, 2025; Apertus 8B came out Sep 2, 2025. Knowledge cutoff: Apertus 8B Sep 2025, Nemotron 3 Nano 30B A3B Jun 25, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
