qwopus3.6-27b-coder-compat-mtp
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
88 vs 86
Hardware Fit
80 vs 78
Quality Score
91 vs 89
Hardware
qwopus3.6-27b-code… Kimi-48B:48B
MachineASUSGMKtec NucBox EVO-T2S
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorIntel Core™ Ultra X7 358H
Cores1616
RAM31 GB64 GB
GPUNVIDIA GeForce RTX 4090, RaphaelIntel(R) Arc(TM) B390 GPU
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
qwopus3.6-27b-code… Kimi-48B:48B
Tokens/sec42.923.1
First chunk32 ms752 ms
TTFT413 ms752 ms
Load timeN/A22.2 s
Memory usage24.6 GB25.5 GB
Memory %81%40%
HW Fit Score Breakdown
qwopus3.6-27b-coder-com…
Speed
50/50
TTFT
20/20
Memory
10/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
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
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
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