Back to leaderboard

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 11, 2026 · Intel Core™ i5-8350U

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

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
73 vs 88
Hardware Fit
93 vs 80
Quality Score
65 vs 91

Hardware

lfm2.5:latest qwopus3.6-27b-code…
MachineLENOVO 20L7CTO1WWASUS
CPUIntel Core™ i5-8350UAMD Ryzen 7 7800X3D 8-Core Processor
Cores816
RAM23 GB31 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 4090, Raphael
OSFedora Linux 44cachyos rolling
Archx64x64
Power Modeperformanceperformance

Performance

lfm2.5:latest qwopus3.6-27b-code…
Tokens/sec18.380.8
First chunk981 ms6 ms
TTFT981 ms226 ms
Load time8.0 sN/A
Memory usage4.9 GB24.6 GB
Memory %21%81%

HW Fit Score Breakdown

lfm2.5:latest

Speed
43/50
TTFT
20/20
Memory
30/30

qwopus3.6-27b-coder-com…

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

Quality

lfm2.5:latest

Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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