Gemma 4 E2B vs Ternary Bonsai 4B

At a Glance

Compare
Gemma 4 E2BGoogle DeepMind
Pricing and Limits
Context windowMaximum documented tokens131K33K
Model facts checkedSep 3, 2026View model evidence →Sep 18, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Available Benchmarks

All benchmark results →
No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

Side-by-Side Facts

FieldGemma 4 E2BTernary Bonsai 4B
DeveloperGoogle DeepMindPrismML
FamilyGemma 4Bonsai 4b
ModelGemma 4 E2BTernary Bonsai 4B
VersionGemma 4 E2BTernary Bonsai 4B
Lifecycleactiveactive
Released2026-03-022026-04-18
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, Video, AudioText
Output modalitiesTextText
Context window131K33K
Total parametersUnknown4B
Active parametersUnknownUnknown
Licenseapache-2.0apache-2.0
Open weightsYesYes
API availableYesNo
Self-hostableYesYes
Provider accessTogether Ai (Standard)Unknown
Capabilitieschat, generation, reasoning, structured_outputs, toolschat, generation
Effective bit widthUnknown1.58 bits per weight
Weight sizeUnknown1.07 GB
Weight formatUnknownTernary Q2_0

Gemma 4 E2B Capabilities

chatgenerationreasoningstructured outputstools
Serving providers1
Canonical IDgoogle/gemma-4-E2B-it

Ternary Bonsai 4B Capabilities

chatgeneration
Serving providers0
Canonical IDprism-ml/Ternary-Bonsai-4B

Primary Evidence

Sources and Freshness

Questions

Gemma 4 E2B vs Ternary Bonsai 4B FAQs

Is Gemma 4 E2B or Ternary Bonsai 4B better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Gemma 4 E2B and Ternary Bonsai 4B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Gemma 4 E2B or Ternary Bonsai 4B?+

Neither model has a directly sourced input price in this comparison. Neither model has a directly sourced output price in this comparison.

Which has a larger context window, Gemma 4 E2B or Ternary Bonsai 4B?+

Gemma 4 E2B has the larger sourced context window. Gemma 4 E2B supports 131K and Ternary Bonsai 4B supports 33K.

Which performs better in benchmarks, Gemma 4 E2B or Ternary Bonsai 4B?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can Gemma 4 E2B or Ternary Bonsai 4B be self-hosted?+

Both models have the same recorded self-hosting status: supported. Gemma 4 E2B is open weight; Ternary Bonsai 4B is open weight.

Can Gemma 4 E2B and Ternary Bonsai 4B understand images?+

Gemma 4 E2B is documented with image input; Ternary Bonsai 4B is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Gemma 4 E2B or Ternary Bonsai 4B?+

Neither has a larger sourced maximum output. Gemma 4 E2B is — and Ternary Bonsai 4B is —.

Do Gemma 4 E2B and Ternary Bonsai 4B support reasoning and tool use?+

Gemma 4 E2B: reasoning, tool calling, and image input. Ternary Bonsai 4B: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, Gemma 4 E2B or Ternary Bonsai 4B?+

Gemma 4 E2B has 1 sourced provider route; Ternary Bonsai 4B has 0, so Gemma 4 E2B has broader tracked availability.

Which offers better value, Gemma 4 E2B or Ternary Bonsai 4B?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback