Back to leaderboard

gemma4:26b

OLLAMA GGUF

gemma4 · 25.8B · Q4_K_M

Not Rec.

Apr 3, 2026 · Apple M4

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

Global Score
33 vs 59
Hardware Fit
50 vs 63
Quality Score
25 vs 58

Hardware

gemma4:26b qwen3.8-27b-mlx
MachineMac miniMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM24 GB64 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:26b qwen3.8-27b-mlx
Tokens/sec20.018.3
First chunk941 ms4 ms
TTFT30.0 s530 ms
Load time0.2 sN/A
Memory usage20.3 GB38.5 GB
Memory %85%60%

HW Fit Score Breakdown

gemma4:26b

Speed
42/50
TTFT
0/20
Memory
8/30

qwen3.8-27b-mlx

Speed
23/50
TTFT
20/20
Memory
20/30

Quality

gemma4:26b

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.8-27b-mlx

Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
View gemma4:26b details | View qwen3.8-27b-mlx 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