Skip to content
Model Pareto

Ternary Bonsai 2 27B

PrismMLOpen weightsternary (PrismML PTQ1_0)quantized from Qwen3.8 27Bhuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~84tok/sest.
Context
262Ktokens

Open weights (Apache-2.0). Ternary g128 quantization of Qwen3.8-27B; PTQ1_0 GGUF is 5.95 GB (PQ2_0 7.21 GB). Scores are for the quantized weights.

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 (PrismML PTQ1_0) weights
Throughput
~6,364 tok/s
many requests batched
Price
$0.13–1.16 /M tok
busy → light use
On your own machine
RTX 5090 32GB (ternary (PrismML PTQ1_0), ~210 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • TERNARY (PRISMML PTQ1_0) weights (27.36B params) + 25% KV-cache headroom ≈ 7 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~6,364 output tok/s aggregate at batch 182 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~38,857 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
~#3 of 14 (estimated)~82.8%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. ~#3Ternary Bonsai 2 27BEstimated82.8%
  4. #3Gemini 3.1 Pro80.6%
No published score — estimated from related benchmarks
SciCodeEstimated
~#17 of 103 (estimated)~56.1%
  1. #1Claude Opus 5.566.9%
  2. #2Claude Fable 5.163.1%
  3. #16Claude Opus 556.4%
  4. ~#17Ternary Bonsai 2 27BEstimated56.1%
  5. #17DeepSeek V4.1 Flash NVFP455.8%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#5 of 15 (estimated)~59.5
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #4Claude Opus 559.7
  4. ~#5Ternary Bonsai 2 27BEstimated59.5
  5. #5GPT-6 Sol56.7
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#2 of 5 (estimated)~89.2%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2Ternary Bonsai 2 27BEstimated89.2%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#16 of 54 (estimated)~1454 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #15GPT-5.6 Terra1456
  4. ~#16Ternary Bonsai 2 27BEstimated1454
  5. #16DeepSeek V4 Pro (0813)1448
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#16 of 54 (estimated)~1465 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #15GPT-5.6 Terra1466
  4. ~#16Ternary Bonsai 2 27BEstimated1465
  5. #16DeepSeek V4 Pro (0813)1463
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1983 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #8Grok 4.72007
  4. ~#9Ternary Bonsai 2 27BEstimated1983
  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 2 27BEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#5 of 9 (estimated)~81.2%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #4Qwen3.8-Omni-Flash83.5%
  4. ~#5Ternary Bonsai 2 27BEstimated81.2%
  5. #5Muse Glimmer78.8%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~87.3%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Ternary Bonsai 2 27BEstimated87.3%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#16 of 43 (estimated)~17.8%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #15Gemini 3.1 Pro17.8%
  4. ~#16Ternary Bonsai 2 27BEstimated17.8%
  5. #16Grok 4.617.2%
No published score — estimated from related benchmarks
ChartographyEstimated
~#8 of 23 (estimated)~29.7%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #7GPT-5.531.0%
  4. ~#8Ternary Bonsai 2 27BEstimated29.7%
  5. #8GPT-6 Luna29.1%
No published score — estimated from related benchmarks

Hard reasoning

GPQA DiamondEstimated
~#37 of 180 (estimated)~88.5%
  1. #1GPT-6 Astra96.1%
  2. #2Gemini 3.8 Flash95.3%
  3. #36Solar Pro 489.1%
  4. ~#37Ternary Bonsai 2 27BEstimated88.5%
  5. #37Qwen3.8 27B NVFP488.0%
No published score — estimated from related benchmarks
Humanity's Last ExamEstimated
~#37 of 182 (estimated)~34.0%
  1. #1Claude Opus 5.561.4%
  2. #2Claude Fable 5.159.1%
  3. #36Apodex 1.134.1%
  4. ~#37Ternary Bonsai 2 27BEstimated34.0%
  5. #37Qwen3.8 27B33.9%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#22 of 78 (estimated)~39.1
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #21DeepSeek V4.1 Flash39.5
  4. ~#22Ternary Bonsai 2 27BEstimated39.1
  5. #22GPT-5.538.4
No published score — estimated from related benchmarks