qwopus3.6-27b-coder-compat-mtp
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
Global Score
88 vs 76
Hardware Fit
80 vs 46
Quality Score
91 vs 89
Hardware
qwopus3.6-27b-code… gemma4:31b
MachineASUSMacBook Pro
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M4 Max
Cores1616
RAM31 GB64 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M4 Max
OScachyos rollingmacOS 26.3.1
Archx64arm64
Power Modeperformancebalanced
Performance
qwopus3.6-27b-code… gemma4:31b
Tokens/sec42.922.4
First chunk32 ms565 ms
TTFT413 ms30.0 s
Load timeN/A6.9 s
Memory usage24.6 GB43.9 GB
Memory %81%69%
HW Fit Score Breakdown
qwopus3.6-27b-coder-com…
Speed
50/50
TTFT
20/20
Memory
10/30
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
Quality
qwopus3.6-27b-coder-com…
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest