Back to leaderboard

lfm2:24b-a2b

OLLAMA GGUF

lfm2moe · 23.8B · Q4_K_M

Good

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

granite-3.3-2b-instruct

LM-STUDIO MLX

granite · 2B · bf16

Good

Mar 4, 2026 · Apple M4

Global Score
78 vs 66
Hardware Fit
67 vs 87
Quality Score
82 vs 57

Hardware

lfm2:24b-a2b granite-3.3-2b-ins…
MachineDell Inc. Inspiron 15 3530MacBook Air
CPUIntel Gen Intel® Core™ i7-1355UApple M4
Cores1210
RAM31 GB32 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M4
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced

Performance

lfm2:24b-a2b granite-3.3-2b-ins…
Tokens/sec11.518.3
First chunk1727 ms541 ms
TTFT1.7 s541 ms
Load time6.8 sN/A
Memory usage13.9 GB4.7 GB
Memory %45%15%

HW Fit Score Breakdown

lfm2:24b-a2b

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

granite-3.3-2b-instruct

Speed
37/50
TTFT
20/20
Memory
30/30

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

granite-3.3-2b-instruct

Reasoning
10/20
Coding
10/20
Instruction
14/20
Structured
14/15
Math
2/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View lfm2:24b-a2b details | View granite-3.3-2b-ins… details

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