Back to leaderboard

prism-ml/bonsai-27b

LM-STUDIO GGUF

qwen35 · 27B · Q1_0

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score
81 vs 65
Hardware Fit
95 vs 96
Quality Score
75 vs 51

Hardware

prism-ml/bonsai-27b qwen3-4b-qwen3.6-p…
MachineASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PHMac Studio
CPUAMD Ryzen 9 8940HXApple M2 Max
Cores3212
RAM15 GB96 GB
GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610MApple M2 Max
OSMicrosoft Windows 11 Home Single Language 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

prism-ml/bonsai-27b qwen3-4b-qwen3.6-p…
Tokens/sec33.699.6
First chunk20 ms18 ms
TTFT409 ms1.6 s
Load timeN/A4.8 s
Memory usage5.3 GB0.3 GB
Memory %35%0%

HW Fit Score Breakdown

prism-ml/bonsai-27b

Speed
46/50
TTFT
20/20
Memory
29/30

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
Memory
30/30

Quality

prism-ml/bonsai-27b

Reasoning
17/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest