Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

lfm2.5:latest

OLLAMA GGUF

lfm2moe · 8.5B · Q4_K_M

Good

Jun 11, 2026 · Intel Core™ i5-8350U

Global Score
64 vs 73
Hardware Fit
69 vs 93
Quality Score
62 vs 65

Hardware

qwen3.5:4b lfm2.5:latest
MachineLENOVO 20U30029MBLENOVO 20L7CTO1WW
CPUIntel Core™ i5-10210UIntel Core™ i5-8350U
Cores88
RAM15 GB23 GB
GPUCometLake-U GT2 [UHD Graphics]Kaby Lake-R GT2 [UHD Graphics 620]
OSPop 24.04 LTSFedora Linux 44
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.5:4b lfm2.5:latest
Tokens/sec7.418.3
First chunk1815 ms981 ms
TTFT1.8 s981 ms
Load time10.9 s8.0 s
Memory usage3.5 GB4.9 GB
Memory %23%21%

HW Fit Score Breakdown

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

lfm2.5:latest

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

Quality

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong

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

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