Ternary Bonsai 2 27B
API request failed. The model was not evaluated.
PrismMLLanguage modelOpen source
Ternary Bonsai 2 27B has no overall index value yet because there are too few independent benchmark results. From the vendor-reported results we estimate about 72.8 points (95% range 52.4 to 93.1). This is not an independent measurement.
n/ano search or usage data
Ternary Bonsai 2 27B compresses Qwen3.8-27B into ternary weights. According to PrismML, the densely packed PTQ1_0 files need 5.95 GB for the language model and store 1.75 bits per weight. A separately supplied vision component is added for image input.
The full checkpoint has 27.36 billion parameters and handles 262,144 context tokens. It retains the base model’s architecture. PrismML releases the weights under Apache 2.0, with the idealized ternary precision of 1.72 bits differing from the shipped PTQ1_0 format.
On this page
One SVG task with the same fixed settings for every model, without hidden thinking.
API request failed. The model was not evaluated.
This is the lowest documented setting for each provider. It does not make compute comparable across models.

Prompt
Generate an SVG of a pelican riding a bicycle
Oct 11, 2026 · 104 s · $0.0022
Visually reviewed. This individual test does not establish overall model quality.
Every published result with its source, test setup and comparison models.
Page 1 of 6
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Page 1 of 6
More models of the same kind as Ternary Bonsai 2 27B, chosen by model line, developer, size, price and release date.
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
Independent results are not yet enough for the overall index. An estimate from 5 vendor-reported results (AIME 2025 95%, GPQA Diamond 85.8%, LiveCodeBench v6 90.1%, SWE-bench Verified 60.8%, Terminal-Bench 2.1 52.8%) gives about 72.8 points, with a 95% range of 52.4 to 93.1. The estimate is calibrated on models with both vendor-reported and independent results. Vendor numbers run clearly above independent measurements on some tests; the calibration offsets that on average.
Vendor estimate, not an overall index value
262,144 tokens. Separate limits may apply to input and output.
Yes, the weights are open.
Stated by PrismML
Which independent evaluators tested this model. This is coverage, not a quality ranking.
No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.
Without vendor claims and historical or disputed results; those stay labelled in the single values.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 12 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not published | category-aggregation Note The release page lists the component benchmarks per category but does not publish the score scale, aggregation formula, individual component scores for each category, denominators, prompting, decoding settings or evaluation date. |
| Unresolved | profile-specific-generalization Note The external report explicitly treats reasoning-off as a separate material profile and does not support transfer to reasoning-on or other quantizations. The team roster has no separate per-configuration model ID, so the exact distinction is retained in every score configuration and caveat. |
| Unresolved | separate prefill-curve result Note The report separately lists a prefill curve with pp512 293 tok/s while the llama-bench table reports 313.0 tok/s for dual T4; the curve's method/context is not sufficiently specified to merge or substitute, so it was not added. |
| Additional source | PrismML Bonsai 2 27B announcement (retrieved October 3, 2026; October 17, 2026) · PrismML Bonsai 2 27B announcement · Editorial description reviewed October 4, 2026 |
| Additional source | Ternary Bonsai 2 model card (retrieved October 3, 2026) · Ternary Bonsai 2 model card · Editorial description reviewed October 4, 2026 |
| Additional source | PrismML whitepaper Tables 7, 8, 10 and methodology (retrieved October 4, 2026) |
| Additional source | WumboLabs, Bonsai 2 27B WELP methodology-revision supplement (retrieved October 17, 2026) |
| Additional source | Bonsai-demo community benchmark report (retrieved October 18, 2026) |
| Additional source | Bonsai-demo community issue #181 by xzphot (retrieved October 18, 2026) |
| Additional source | PrismML Bonsai 2 community benchmarks, RTX 5090 Linux report (retrieved October 18, 2026) |
| Additional source | PrismML Bonsai 2 community benchmarks, RTX 5080 Windows report (retrieved October 18, 2026) |
| Additional source | instax-dutta GitHub Gist (retrieved October 19, 2026) |
| Additional source | Tsotchke Corporation / GeoRefine, What ternary keeps, and what it loses (retrieved October 22, 2026) |
| Additional source | WumboLabs WELP methodology-revision supplement, thinking-off profile (retrieved October 23, 2026) |
| Additional source | Model metadata (retrieved October 17, 2026; October 23, 2026) |
| Additional source | Model metadata (retrieved October 18, 2026) |