Back to leaderboard

lfm2:24b-a2b

OLLAMA GGUF

lfm2moe · 23.8B · Q4_K_M

Good

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

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Excellent

Aug 24, 2026 · Intel Core™ Ultra X7 358H

Global Score
78 vs 82
Hardware Fit
67 vs 59
Quality Score
82 vs 92

Hardware

lfm2:24b-a2b Qwen3-80B:80B
MachineDell Inc. Inspiron 15 3530GMKtec NucBox EVO-T2S
CPUIntel Gen Intel® Core™ i7-1355UIntel Core™ Ultra X7 358H
Cores1216
RAM31 GB64 GB
GPURaptor Lake-P [Iris Xe Graphics]Intel(R) Arc(TM) B390 GPU
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

lfm2:24b-a2b Qwen3-80B:80B
Tokens/sec11.519.6
First chunk1727 ms823 ms
TTFT1.7 s823 ms
Load time6.8 s41.6 s
Memory usage13.9 GB46.9 GB
Memory %45%74%

HW Fit Score Breakdown

lfm2:24b-a2b

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

Qwen3-80B:80B

Speed
26/50
TTFT
20/20
Memory
13/30

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

Qwen3-80B:80B

Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
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