Back to leaderboard

qwen3.8-27b-mlx

LM-STUDIO MLX

qwen3_5 · 27B · 8bit

Marginal

Aug 17, 2026 · Apple M5 Max

gemma4:26b-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

Global Score
59 vs 85
Hardware Fit
63 vs 80
Quality Score
58 vs 87

Hardware

qwen3.8-27b-mlx gemma4:26b-nvfp4
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M4 Pro
Cores1814
RAM64 GB48 GB
GPUApple M5 MaxApple M4 Pro
OSmacOS 27.0macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-mlx gemma4:26b-nvfp4
Tokens/sec18.365.7
First chunk4 ms233 ms
TTFT530 ms30.0 s
Load timeN/A5.0 s
Memory usage38.5 GB15.2 GB
Memory %60%32%

HW Fit Score Breakdown

qwen3.8-27b-mlx

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

gemma4:26b-nvfp4

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

Quality

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

gemma4:26b-nvfp4

Reasoning
17/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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