Back to leaderboard

lfm2-24b-a2b

LM-STUDIO GGUF
Not Rec.

Mar 6, 2026 · Apple M4 Pro

deepseek-r1:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

Global Score
18 vs 22
Hardware Fit
59 vs 50
Quality Score
0 vs 10

Hardware

lfm2-24b-a2b deepseek-r1:14b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

lfm2-24b-a2b deepseek-r1:14b
Tokens/sec6.611.4
First chunk1025 msN/A
TTFT1.0 s30.0 s
Load timeN/A1.0 s
Memory usage0.0 GB16.5 GB
Memory %0%52%

HW Fit Score Breakdown

lfm2-24b-a2b

Speed
9/50
TTFT
20/20
Memory
30/30

deepseek-r1:14b

Speed
20/50
TTFT
0/20
Memory
30/30

Quality

lfm2-24b-a2b

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

deepseek-r1:14b

Reasoning
1/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
5/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate
View lfm2-24b-a2b details | View deepseek-r1:14b 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