Back to leaderboard

prism-ml/bonsai-27b

LM-STUDIO GGUF

qwen35 · 27B · Q1_0

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

phi4:latest

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
81 vs 85
Hardware Fit
95 vs 100
Quality Score
75 vs 79

Hardware

prism-ml/bonsai-27b phi4:latest
MachineASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PHGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD Ryzen 9 8940HXIntel Core™ i5-14400F
Cores3216
RAM15 GB32 GB
GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610MNVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Home Single Language 10.0.26200Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

prism-ml/bonsai-27b phi4:latest
Tokens/sec33.638.3
First chunk20 ms72 ms
TTFT409 ms72 ms
Load timeN/A6.2 s
Memory usage5.3 GB9.1 GB
Memory %35%29%

HW Fit Score Breakdown

prism-ml/bonsai-27b

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

phi4:latest

Speed
50/50
TTFT
20/20
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

phi4:latest

Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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