Back to leaderboard

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

qwen3.8:latest

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Good

Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor

Global Score
71 vs 68
Hardware Fit
35 vs 22
Quality Score
86 vs 88

Hardware

google/gemma-3-27b qwen3.8:latest
MachineMac miniSystem manufacturer
CPUApple M4AMD Ryzen 9 5950X 16-Core Processor
Cores1032
RAM24 GB32 GB
GPUApple M4NVIDIA GeForce RTX 3090
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced

Performance

google/gemma-3-27b qwen3.8:latest
Tokens/sec5.910.0
First chunk19 ms1041 ms
TTFT1.8 s14.3 s
Load timeN/A22.3 s
Memory usage22.0 GB26.2 GB
Memory %92%82%

HW Fit Score Breakdown

google/gemma-3-27b

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

qwen3.8:latest

Speed
12/50
TTFT
1/20
Memory
9/30

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

qwen3.8:latest

Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View google/gemma-3-27b details | View qwen3.8:latest 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