Back to leaderboard

qwen/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 18, 2026 · Apple M4 Max

gemma-4-26b-a4b-it-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_K_XL

Excellent

Jul 7, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
87 vs 88
Hardware Fit
83 vs 77
Quality Score
88 vs 93

Hardware

qwen/qwen3.8-27b gemma-4-26b-a4b-it…
MachineMacBook ProASUS
CPUApple M4 MaxAMD Ryzen 7 7800X3D 8-Core Processor
Cores1616
RAM128 GB31 GB
GPUApple M4 MaxNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.5.2cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen/qwen3.8-27b gemma-4-26b-a4b-it…
Tokens/sec29.1170.5
First chunk9 ms13 ms
TTFT650 ms121 ms
Load timeN/AN/A
Memory usage21.0 GB26.0 GB
Memory %16%85%

HW Fit Score Breakdown

qwen/qwen3.8-27b

Speed
33/50
TTFT
20/20
Memory
30/30

gemma-4-26b-a4b-it-qat

Speed
50/50
TTFT
20/20
Memory
7/30

Quality

qwen/qwen3.8-27b

Reasoning
18/20
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

gemma-4-26b-a4b-it-qat

Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen/qwen3.8-27b details | View gemma-4-26b-a4b-it… 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