Skip to content
Model Pareto

Ternary Bonsai 27B

PrismMLOpen weightsternary (Q2_0_g128)huggingface.co ↗
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

~#5 of 21 (estimated)~80.6%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #4Gemini 3.1 Pro80.6%
  4. ~#5Ternary Bonsai 27BEstimated80.6%
  5. #5MiniMax-M380.5%
No published score — estimated from related benchmarks
~#9 of 24 (estimated)~65.6%
  1. #1Claude Fable 5.293.0%
  2. #2Claude Opus 5.589.9%
  3. #8Hy4 preview65.7%
  4. ~#9Ternary Bonsai 27BEstimated65.6%
  5. #9GPT-5.6 Terra63.4%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#43 of 46 (estimated)~33.3%
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash 101777.0%
  3. #42Nex-N2.5-Mini36.1%
  4. ~#43Ternary Bonsai 27BEstimated33.3%
  5. #43Hy328.0%
No published score — estimated from related benchmarks
SciCodeEstimated
~#36 of 119 (estimated)~53.2%
  1. #1Claude Fable 5.267.7%
  2. #2Claude Opus 5.566.9%
  3. #35MiniMax-M3.1-Flash53.4%
  4. ~#36Ternary Bonsai 27BEstimated53.2%
  5. #36Grok 4.653.0%
No published score — estimated from related benchmarks
~#11 of 26 (estimated)~50.2
  1. #1Claude Opus 5.561.7
  2. #2Claude Opus 559.7
  3. #10Muse Wonder52.0
  4. ~#11Ternary Bonsai 27BEstimated50.2
  5. #11GLM-5.348.9
No published score — estimated from related benchmarks

Writing & chat

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
~#9 of 12 (estimated)~78.4%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #8Muse Glimmer78.8%
  4. ~#9Ternary Bonsai 27BEstimated78.4%
  5. #9Inkling78.1%
No published score — estimated from related benchmarks
~#4 of 8 (estimated)~85.3%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Ternary Bonsai 27BEstimated85.3%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#26 of 48 (estimated)~14.4%
  1. #1Muse Wonder Full32.6%
  2. #2GPT-6 Astra31.0%
  3. #25Step 5 Preview14.8%
  4. ~#26Ternary Bonsai 27BEstimated14.4%
  5. #26Gemini 3.5 Flash-Lite13.6%
No published score — estimated from related benchmarks
ChartographyEstimated
~#17 of 25 (estimated)~20.1%
  1. #1Claude Fable 5.273.4%
  2. #2GPT-6 Astra71.0%
  3. #16Grok 4.620.5%
  4. ~#17Ternary Bonsai 27BEstimated20.1%
  5. #17Muse Glimmer17.2%
No published score — estimated from related benchmarks

Hard reasoning