Back to leaderboard

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 11, 2026 · Intel Core™ i5-8350U

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
73 vs 88
Hardware Fit
93 vs 85
Quality Score
65 vs 89

Hardware

lfm2.5:latest huihui-qwen3.6-35b…
MachineLENOVO 20L7CTO1WWGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i5-8350UAMD Ryzen 5 5600X 6-Core Processor
Cores812
RAM23 GB47 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]AD106 [GeForce RTX 4060 Ti]
OSFedora Linux 44cachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

lfm2.5:latest huihui-qwen3.6-35b…
Tokens/sec18.337.7
First chunk981 ms18 ms
TTFT981 ms2.9 s
Load time8.0 sN/A
Memory usage4.9 GB26.1 GB
Memory %21%56%

HW Fit Score Breakdown

lfm2.5:latest

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

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

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

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
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