Back to leaderboard

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

prism-ml/bonsai-27b

LM-STUDIO GGUF

qwen35 · 27B · Q1_0

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
71 vs 81
Hardware Fit
35 vs 95
Quality Score
86 vs 75

Hardware

google/gemma-3-27b prism-ml/bonsai-27b
MachineMac miniASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUApple M4AMD Ryzen 9 8940HX
Cores1032
RAM24 GB15 GB
GPUApple M4NVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSmacOS 26.3Microsoft Windows 11 Home Single Language 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

google/gemma-3-27b prism-ml/bonsai-27b
Tokens/sec5.933.6
First chunk19 ms20 ms
TTFT1.8 s409 ms
Load timeN/AN/A
Memory usage22.0 GB5.3 GB
Memory %92%35%

HW Fit Score Breakdown

google/gemma-3-27b

Speed
12/50
TTFT
19/20
Memory
4/30

prism-ml/bonsai-27b

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

Quality

google/gemma-3-27b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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
View google/gemma-3-27b details | View prism-ml/bonsai-27b details

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