Back to leaderboard

qwopus3.6-27b-coder-compat-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

google/gemma-4-26b-a4b-qat

LM-STUDIO GGUF

gemma4 · 26B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
88 vs 93
Hardware Fit
80 vs 96
Quality Score
91 vs 92

Hardware

qwopus3.6-27b-code… google/gemma-4-26b…
MachineASUSMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM31 GB31 GB
GPUNVIDIA GeForce RTX 4090, RaphaelNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwopus3.6-27b-code… google/gemma-4-26b…
Tokens/sec42.9109.7
First chunk32 ms29 ms
TTFT413 ms156 ms
Load timeN/AN/A
Memory usage24.6 GB14.6 GB
Memory %81%47%

HW Fit Score Breakdown

qwopus3.6-27b-coder-com…

Speed
50/50
TTFT
20/20
Memory
10/30

google/gemma-4-26b-a4b-…

Speed
50/50
TTFT
20/20
Memory
26/30

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

google/gemma-4-26b-a4b-…

Reasoning
18/20
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

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