Sarvam 30B vs Stockmark 2 100B Instruct
Sarvam 30B (2026) and Stockmark 2 100B Instruct (2025) are compact production models from Sarvam.ai and Stockmark. Sarvam 30B ships a 65.5k-token context window, while Stockmark 2 100B Instruct ships a 128K-token context window. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit. It focuses on practical selection signals rather than broad model-family marketing. The goal is to make the tradeoff clear before deeper testing.
Sarvam 30B is safer overall; choose Stockmark 2 100B Instruct when long-context analysis matters.
Decision scorecard
Local evidence first| Signal | Sarvam 30B | Stockmark 2 100B Instruct |
|---|---|---|
| Decision fit | Agents and JSON / Tool use | Long context |
| Context window | 65.5k | 128K |
| Cheapest output | - | - |
| Provider routes | 0 tracked | 1 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- Sarvam 30B uniquely exposes Function calling and Tool use in local model data.
- Local decision data tags Sarvam 30B for Agents and JSON / Tool use.
- Stockmark 2 100B Instruct has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Stockmark 2 100B Instruct has broader tracked provider coverage for fallback and procurement flexibility.
- Local decision data tags Stockmark 2 100B Instruct for Long context.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output prices on this page.
Sarvam 30B
Unavailable
No complete token price in local provider data
Stockmark 2 100B Instruct
Unavailable
No complete token price in local provider data
Cost delta unavailable until both models have sourced input and output token prices.
Switch friction
- No overlapping tracked provider route is sourced for Sarvam 30B and Stockmark 2 100B Instruct; plan for SDK, billing, or endpoint changes.
- Check replacement coverage for Function calling and Tool use before moving production traffic.
- No overlapping tracked provider route is sourced for Stockmark 2 100B Instruct and Sarvam 30B; plan for SDK, billing, or endpoint changes.
- Sarvam 30B adds Function calling and Tool use in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2026-03-22 | 2025-06-01 |
| Context window | 65.5k | 128K |
| Parameters | 30B (2.4B active) | 100B |
| Architecture | moe | decoder only |
| License | Apache 2.0 | 1 |
| Knowledge cutoff | - | - |
Pricing and availability
| Pricing attribute | Sarvam 30B | Stockmark 2 100B Instruct |
|---|---|---|
| Input price | - | - |
| Output price | - | - |
| Providers | - |
Pricing not yet sourced for either model.
Capabilities
| Capability | Sarvam 30B | Stockmark 2 100B Instruct |
|---|---|---|
| Vision | No | No |
| Multimodal | No | No |
| Reasoning | No | No |
| Function calling | Yes | No |
| Tool use | Yes | No |
| Structured outputs | No | No |
| Code execution | No | No |
Benchmarks
No shared benchmark rows are currently sourced for this pair.
Deep dive
The capability footprint differs most on function calling: Sarvam 30B and tool use: Sarvam 30B. Both models share the core language-model surface, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
Pricing coverage is uneven: Sarvam 30B has no token price sourced yet and Stockmark 2 100B Instruct has no token price sourced yet. Provider availability is 0 tracked routes versus 1. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.
Choose Sarvam 30B when provider fit are central to the workload. Choose Stockmark 2 100B Instruct when long-context analysis, larger context windows, and broader provider choice are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions. It also helps separate model capability from provider packaging, which can change cost and latency. For teams standardizing a stack, that distinction is often the difference between a benchmark win and a reliable deployment.
FAQ
Which has a larger context window, Sarvam 30B or Stockmark 2 100B Instruct?
Stockmark 2 100B Instruct supports 128K tokens, while Sarvam 30B supports 65.5k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Is Sarvam 30B or Stockmark 2 100B Instruct open source?
Sarvam 30B is listed under Apache 2.0. Stockmark 2 100B Instruct is listed under 1. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for function calling, Sarvam 30B or Stockmark 2 100B Instruct?
Sarvam 30B has the clearer documented function calling signal in this comparison. If function calling is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for tool use, Sarvam 30B or Stockmark 2 100B Instruct?
Sarvam 30B has the clearer documented tool use signal in this comparison. If tool use is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run Sarvam 30B and Stockmark 2 100B Instruct?
Sarvam 30B is available on the tracked providers still being sourced. Stockmark 2 100B Instruct is available on NVIDIA NIM. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
When should I pick Sarvam 30B over Stockmark 2 100B Instruct?
Sarvam 30B is safer overall; choose Stockmark 2 100B Instruct when long-context analysis matters. If your workload also depends on provider fit, start with Sarvam 30B; if it depends on long-context analysis, run the same evaluation with Stockmark 2 100B Instruct.
Continue comparing
Last reviewed: 2026-05-01. Data sourced from public model cards and provider documentation.