Back to leaderboard

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

qwen2.5vl:3b

OLLAMA GGUF

qwen25vl · 3.8B · Q4_K_M

Good

Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H

Global Score
71 vs 77
Hardware Fit
35 vs 100
Quality Score
86 vs 67

Hardware

google/gemma-3-27b qwen2.5vl:3b
MachineMac miniMicro-Star International Co., Ltd. Stealth GS77 12UH
CPUApple M4Intel Gen Intel® Core™ i9-12900H
Cores1020
RAM24 GB32 GB
GPUApple M4Intel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPU
OSmacOS 26.3Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

google/gemma-3-27b qwen2.5vl:3b
Tokens/sec5.9106.5
First chunk19 ms68 ms
TTFT1.8 s68 ms
Load timeN/A17.8 s
Memory usage22.0 GB2.8 GB
Memory %92%9%

HW Fit Score Breakdown

google/gemma-3-27b

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

qwen2.5vl:3b

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

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

qwen2.5vl:3b

Reasoning
11/20
Coding
15/20
Instruction
12/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View google/gemma-3-27b details | View qwen2.5vl:3b 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