Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

prism-ml/bonsai-27b

LM-STUDIO GGUF

qwen35 · 27B · Q1_0

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
68 vs 81
Hardware Fit
93 vs 95
Quality Score
57 vs 75

Hardware

google/gemma-4-e4b prism-ml/bonsai-27b
MachineLENOVO 82JQASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUAMD Ryzen 7 5800HAMD Ryzen 9 8940HX
Cores1632
RAM16 GB15 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b prism-ml/bonsai-27b
Tokens/sec26.233.6
First chunk17 ms20 ms
TTFT572 ms409 ms
Load timeN/AN/A
Memory usage6.5 GB5.3 GB
Memory %41%35%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

prism-ml/bonsai-27b

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

Quality

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor

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-4-e4b 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