Gemma 4 E4B vs Bonsai Image Ternary 4B

At a Glance

Compare
Gemma 4 E4BGoogle DeepMind
Pricing and Limits
Input priceFrom · USD / 1M tokens$0.020Deepinfra · Sep 21, 2026Not reported
Output priceFrom · USD / 1M tokens$0.10Deepinfra · Sep 21, 2026Not reported
Context windowMaximum documented tokens131KNot reported
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 E4BBonsai Image Ternary 4B
DeveloperGoogle DeepMindPrismML
FamilyGemma 4Bonsai Image 4b
ModelGemma 4 E4BBonsai Image Ternary 4B
VersionGemma 4 E4BBonsai Image Ternary 4B
Lifecycleactiveactive
Released2026-03-022026-05-21
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, Video, AudioText
Output modalitiesTextImage
Context window131KUnknown
Total parametersUnknown4B
Active parametersUnknownUnknown
Licenseapache-2.0apache-2.0
Open weightsYesYes
API availableYesNo
Self-hostableYesYes
Provider accessDeepinfra (Standard), Together Ai (Standard)Unknown
Capabilitieschat, generation, reasoning, structured_outputs, toolsgeneration
Base modelUnknownFLUX.2 Klein 4B
Default resolutionUnknown512 × 512
Transformer sizeUnknown1.21 GB
Weight formatUnknownTernary weights with FP16 group scales

Gemma 4 E4B Capabilities

chatgenerationreasoningstructured outputstools
Serving providers2
Canonical IDgoogle/gemma-4-E4B-it

Bonsai Image Ternary 4B Capabilities

generation
Serving providers0
Canonical IDprism-ml/Bonsai-Image-Ternary-4B

Primary Evidence

Sources and Freshness

Questions

Gemma 4 E4B vs Bonsai Image Ternary 4B FAQs

Is Gemma 4 E4B or Bonsai Image Ternary 4B better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Gemma 4 E4B and Bonsai Image Ternary 4B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Gemma 4 E4B or Bonsai Image Ternary 4B?+

Only Gemma 4 E4B has a directly sourced input price: $0.020 per million tokens. Only Gemma 4 E4B has a directly sourced output price: $0.10 per million tokens.

Which has a larger context window, Gemma 4 E4B or Bonsai Image Ternary 4B?+

Neither model has a larger sourced context window in this comparison. Gemma 4 E4B is 131K and Bonsai Image Ternary 4B is —.

Which performs better in benchmarks, Gemma 4 E4B or Bonsai Image Ternary 4B?+

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

Can Gemma 4 E4B or Bonsai Image Ternary 4B be self-hosted?+

Both models have the same recorded self-hosting status: supported. Gemma 4 E4B is open weight; Bonsai Image Ternary 4B is open weight.

Can Gemma 4 E4B and Bonsai Image Ternary 4B understand images?+

Gemma 4 E4B is documented with image input; Bonsai Image Ternary 4B is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Gemma 4 E4B or Bonsai Image Ternary 4B?+

Neither has a larger sourced maximum output. Gemma 4 E4B is — and Bonsai Image Ternary 4B is —.

Do Gemma 4 E4B and Bonsai Image Ternary 4B support reasoning and tool use?+

Gemma 4 E4B: reasoning, tool calling, and image input. Bonsai Image Ternary 4B: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, Gemma 4 E4B or Bonsai Image Ternary 4B?+

Gemma 4 E4B has 2 sourced provider routes; Bonsai Image Ternary 4B has 0, so Gemma 4 E4B has broader tracked availability.

Which offers better value, Gemma 4 E4B or Bonsai Image Ternary 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