Back to leaderboard

qwen3.8-27b-claude-opus-reasoning-distilled

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Aug 20, 2026 · Apple M4 Max

gemma4:26b-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

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

Hardware

qwen3.8-27b-claude… gemma4:26b-nvfp4
MachineMacBook ProMacBook Pro
CPUApple M4 MaxApple M4 Pro
Cores1614
RAM128 GB48 GB
GPUApple M4 MaxApple M4 Pro
OSmacOS 26.5.2macOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.8-27b-claude… gemma4:26b-nvfp4
Tokens/sec24.065.7
First chunk20 ms233 ms
TTFT4.5 s30.0 s
Load timeN/A5.0 s
Memory usage15.7 GB15.2 GB
Memory %12%32%

HW Fit Score Breakdown

qwen3.8-27b-claude-opus…

Speed
27/50
TTFT
6/20
Memory
30/30

gemma4:26b-nvfp4

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

Quality

qwen3.8-27b-claude-opus…

Reasoning
19/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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