Back to leaderboard

lfm2:24b-a2b

OLLAMA GGUF

lfm2moe · 23.8B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
78 vs 78
Hardware Fit
67 vs 47
Quality Score
82 vs 92

Hardware

lfm2:24b-a2b gemma4:31b
MachineDell Inc. Inspiron 15 3530AZW GTR Pro
CPUIntel Gen Intel® Core™ i7-1355UAMD RYZEN AI MAX+ 395
Cores1232
RAM31 GB125 GB
GPURaptor Lake-P [Iris Xe Graphics]Radeon 8060S
OScachyos rollingUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerperformance

Performance

lfm2:24b-a2b gemma4:31b
Tokens/sec11.59.8
First chunk1727 ms873 ms
TTFT1.7 s873 ms
Load time6.8 s7.0 s
Memory usage13.9 GB68.3 GB
Memory %45%55%

HW Fit Score Breakdown

lfm2:24b-a2b

Speed
22/50
TTFT
19/20
Memory
26/30

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

Quality

lfm2:24b-a2b

Reasoning
13/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest