Back to leaderboard

liquid/lfm2-24b-a2b

LM-STUDIO MLX

lfm2_moe · 24B · 4bit

Good

Apr 1, 2026 · Apple M4

hf.co/empero-ai/Qwen3.8-4B-Distill-GGUF:Q4_K_M

OLLAMA GGUF

qwen35 · 4.33B · unknown

Good

Aug 28, 2026 · Apple M4

Global Score
74 vs 66
Hardware Fit
84 vs 100
Quality Score
69 vs 52

Hardware

liquid/lfm2-24b-a2b hf.co/empero-ai/Qw…
MachineMac miniMacBook Pro
CPUApple M4Apple M4
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

liquid/lfm2-24b-a2b hf.co/empero-ai/Qw…
Tokens/sec51.826.5
First chunk10 ms447 ms
TTFT503 ms447 ms
Load timeN/A3.3 s
Memory usage17.5 GB4.8 GB
Memory %73%30%

HW Fit Score Breakdown

liquid/lfm2-24b-a2b

Speed
50/50
TTFT
20/20
Memory
14/30

hf.co/empero-ai/Qwen3.8…

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

Quality

liquid/lfm2-24b-a2b

Reasoning
11/20
Coding
12/20
Instruction
16/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

hf.co/empero-ai/Qwen3.8…

Reasoning
18/20
Coding
14/20
Instruction
4/20
Structured
1/15
Math
15/15
Multilingual
0/10
Reasoning: Strong Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

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