ZMIME
Comparison · 2 models · Updated Nov 19, 2026

Dhīr 2B vs Dhīr 5B MoE

No independent capability benchmark covers every model here yet. The score uses context window.

Price in rating: Excluded · Include price

  1. ZenteiQ

    Dhīr 2B

    Released Nov 3, 2026New

    0/100
    • ECI—
    • Price—
    • Context16K
  2. ZenteiQ

    Dhīr 5B MoE

    Released Nov 3, 2026New

    0/100
    • ECI—
    • Price—
    • Context16K
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Dhīr 2B 0/100, Dhīr 5B MoE 0/100) compare the available specifications only. The score weighs context window 100%. 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
  • Longest contextAbout the sameDhīr 2B 16,384 · Dhīr 5B MoE 16,384 tokens
  • Widest inputsSame inputsDhīr 2B: Text · Dhīr 5B MoE: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDhīr 2BDhīr 5B MoE
Context window100%00
Specs only100%0/1000/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Dhīr 2B vs Dhīr 5B MoE specifications side by side
SpecificationDhīr 2BZenteiQDhīr 5B MoEZenteiQ
TaskMultilingual assistantMultilingual assistant
Published capabilitiesDense assistant supporting English and ten Indian languages for offline deployment.Mixture-of-experts assistant supporting English and ten Indian languages for offline deployment.
Model size2.03B parameters5.09B total / 1.79B active
AccessOpen weights for on-premises or offline useOpen weights for on-premises or offline use
SourcesPublisher documentation · Additional documentationPublisher documentation · Additional documentation
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input——
Output——
Cached input——
Blended (3:1)——
Long-context rate——
Price source——
Limits
Context window16,384 tokens16,384 tokens
Max output——
Inputs and features
TextYesYes
ImagesNoNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningUnconfirmedUnconfirmed
Tool calling——
Structured output——
Availability
WeightsOpenOpen
API model ID——
API providers——
ReleasedNov 3, 2026Nov 3, 2026
Knowledge cutoff——
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Dhīr 2B—
  • Dhīr 5B MoE—
04 — Questions

Which should you choose?

Which is better: Dhīr 2B or Dhīr 5B MoE?

There is not enough shared capability evidence to name an overall winner. The scores (Dhīr 2B 0/100, Dhīr 5B MoE 0/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Dhīr 2B or Dhīr 5B MoE?

None of these models has a published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Dhīr 2B has not been scored yet and Dhīr 5B MoE has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Dhīr 2B and Dhīr 5B MoE yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Dhīr 2B and Dhīr 5B MoE has no confirmed tool-calling support in this comparison.

Which has the bigger context window?

Dhīr 2B and Dhīr 5B MoE share the same 16,384-token context window.

Which can read images, PDFs, audio or video?

Dhīr 2B accepts text; Dhīr 5B MoE accepts text. They handle the same number of input types.

Are any of these open source?

Yes, both publish their weights, so you can self-host them.

Which is newer?

Dhīr 2B is the newest, released Nov 3, 2026. Dhīr 5B MoE came out Nov 3, 2026.

How do you decide the winner?

This rating uses context window (100%, 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 19, 2026.