LLM Reference

Together AI - Gemma 3n-e4B vs Stockmark 2 100B Instruct

Together AI - Gemma 3n-e4B (2026) and Stockmark 2 100B Instruct (2025) are compact production models from Google DeepMind and Stockmark. Together AI - Gemma 3n-e4B ships a 8k-token context window, while Stockmark 2 100B Instruct ships a 128k-token context window. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Stockmark 2 100B Instruct fits 16x more tokens; pick it for long-context work and Together AI - Gemma 3n-e4B for tighter calls.

Decision scorecard

Local evidence first
SignalTogether AI - Gemma 3n-e4BStockmark 2 100B Instruct
Best fortool-calling agentsgeneral production evaluation
Decision fitAgents, Classification, and JSON / JSON / Tool useLong context
Context window8k128k
Cheapest output$0.04/1M tokens-
Provider routes1 tracked1 tracked
Shared benchmarks0 shared0 shared

Decision tradeoffs

Choose Together AI - Gemma 3n-e4B when...
  • Together AI - Gemma 3n-e4B uniquely exposes JSON / Tool use and Structured outputs in local model data.
  • Local decision data tags Together AI - Gemma 3n-e4B for Agents, Classification, and JSON / Tool use.
Choose Stockmark 2 100B Instruct when...
  • Stockmark 2 100B Instruct has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • 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 route or tier on this page.

Together AI - Gemma 3n-e4B

$26.00

Cheapest tracked route/tier: Together AI

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

Together AI - Gemma 3n-e4B -> Stockmark 2 100B Instruct
  • No overlapping tracked provider route is sourced for Together AI - Gemma 3n-e4B and Stockmark 2 100B Instruct; plan for SDK, billing, or endpoint changes.
  • Check replacement coverage for JSON / JSON / Tool use and Structured outputs before moving production traffic.
Stockmark 2 100B Instruct -> Together AI - Gemma 3n-e4B
  • No overlapping tracked provider route is sourced for Stockmark 2 100B Instruct and Together AI - Gemma 3n-e4B; plan for SDK, billing, or endpoint changes.
  • Together AI - Gemma 3n-e4B adds JSON / JSON / Tool use and Structured outputs in local capability data.

Specs

Specification
Released2026-03-152025-06-01
Context window8k128k
Parameters4B100B
ArchitectureDecoder OnlyDecoder Only
LicenseGemmaOpen Weights
OpennessOpen weightsOpen weights
WeightsUnknownUnknown
CodeUnknownUnknown
Commercial useCommercial use: conditional-
Knowledge cutoff2024-06-

Pricing and availability

Pricing attributeTogether AI - Gemma 3n-e4BStockmark 2 100B Instruct
Input price$0.02/1M tokens-
Output price$0.04/1M tokens-
Providers

Capabilities

CapabilityTogether AI - Gemma 3n-e4BStockmark 2 100B Instruct
VisionNoNo
MultimodalNoNo
ReasoningNoNo
JSON / Tool useYesNo
Structured outputsYesNo
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark scores are currently available for this pair.

Continue comparing

Last reviewed: 2026-06-29. Data sourced from public model cards and provider documentation.