Skip to content
Model Pareto

Ternary Bonsai 27B

PrismMLOpen weightsternary (Q2_0_g128)huggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~84tok/sest.
Context
262Ktokens

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.

Hardware
1× B200 180GB
ternary (Q2_0_g128) weights
Throughput
~6,372 tok/s
many requests batched
Price
$0.13–1.16 /M tok
busy → light use
On your own machine
RTX 5090 32GB (ternary (Q2_0_g128), ~210 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • TERNARY (Q2_0_G128) weights (27.3B params) + 25% KV-cache headroom ≈ 7 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~6,372 output tok/s aggregate at batch 182 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~38,942 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#5 of 14 (estimated)~80.3%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #4MiniMax-M380.5%
  4. ~#5Ternary Bonsai 27BEstimated80.3%
  5. #5Hy378.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#7 of 19 (estimated)~64.7%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #6Hy4 preview65.7%
  4. ~#7Ternary Bonsai 27BEstimated64.7%
  5. #7GPT-5.6 Terra63.4%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#29 of 32 (estimated)~48.9%
  1. #1GPT-6.1 Sol75.2%
  2. #2DeepSeek V4.1 Flash74.2%
  3. #28Qwen3.8 Max (0902)51.0%
  4. ~#29Ternary Bonsai 27BEstimated48.9%
  5. #29Qwen3.8 27B42.2%
No published score — estimated from related benchmarks
SciCodeEstimated
~#30 of 103 (estimated)~51.6%
  1. #1Claude Opus 5.566.9%
  2. #2Claude Fable 5.163.1%
  3. #29GLM-5.3 Flash51.6%
  4. ~#30Ternary Bonsai 27BEstimated51.6%
  5. #30MiMo-V2.6-Flash51.3%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#9 of 15 (estimated)~52.9
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #8GLM-5.353.6
  4. ~#9Ternary Bonsai 27BEstimated52.9
  5. #9Kimi K351.9
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#3 of 5 (estimated)~86.3%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3Ternary Bonsai 27BEstimated86.3%
  4. #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#29 of 54 (estimated)~1430 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #28Inkling1430
  4. ~#29Ternary Bonsai 27BEstimated1430
  5. #29Qwen3.8 27B1429
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#25 of 54 (estimated)~1442 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #24GPT-5.4 mini1448
  4. ~#25Ternary Bonsai 27BEstimated1442
  5. #25GPT-6 Luna1442
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1932 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #8Grok 4.72007
  4. ~#9Ternary Bonsai 27BEstimated1932
  5. #9Muse Spark 1.31906
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Ternary Bonsai 27BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#7 of 9 (estimated)~77.7%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #6Inkling78.1%
  4. ~#7Ternary Bonsai 27BEstimated77.7%
  5. #7Claude Sonnet 577.0%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~85.4%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Ternary Bonsai 27BEstimated85.4%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#22 of 43 (estimated)~13.4%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #21Gemini 3.5 Flash-Lite13.6%
  4. ~#22Ternary Bonsai 27BEstimated13.4%
  5. #22GPT-5.4 mini13.4%
No published score — estimated from related benchmarks
ChartographyEstimated
~#15 of 23 (estimated)~19.0%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #14Grok 4.620.5%
  4. ~#15Ternary Bonsai 27BEstimated19.0%
  5. #15Muse Glimmer17.2%
No published score — estimated from related benchmarks

Hard reasoning

GPQA DiamondEstimated
~#55 of 180 (estimated)~83.5%
  1. #1GPT-6 Astra96.1%
  2. #2Gemini 3.8 Flash95.3%
  3. #54Gemini 3.5 Flash-Lite83.8%
  4. ~#55Ternary Bonsai 27BEstimated83.5%
  5. #55Muse Glimmer83.5%
No published score — estimated from related benchmarks