qwopus3.6-27b-coder-compat-mtp
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
88 vs 59
Hardware Fit
80 vs 100
Quality Score
91 vs 41
Hardware
qwopus3.6-27b-code… phi:2.7b
MachineASUSMacBook Air
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorApple M4
Cores1610
RAM31 GB32 GB
GPUNVIDIA GeForce RTX 4090, RaphaelApple M4
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
qwopus3.6-27b-code… phi:2.7b
Tokens/sec42.956.6
First chunk32 msN/A
TTFT413 ms110 ms
Load timeN/A0.4 s
Memory usage24.6 GB2.2 GB
Memory %81%7%
HW Fit Score Breakdown
qwopus3.6-27b-coder-com…
Speed
50/50
TTFT
20/20
Memory
10/30
phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
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
phi:2.7b
Reasoning
7/20
Coding
4/20
Instruction
9/20
Structured
11/15
Math
8/15
Multilingual
2/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Poor
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