Back to leaderboard

lfm2-24b-a2b

LM-STUDIO GGUF
Not Rec.

Mar 6, 2026 · Apple M4 Pro

dolphin3:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Good

Mar 6, 2026 · Apple M4

Global Score
18 vs 74
Hardware Fit
59 vs 92
Quality Score
0 vs 66

Hardware

lfm2-24b-a2b dolphin3:8b
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 dolphin3:8b
Tokens/sec6.621.0
First chunk1025 ms314 ms
TTFT1.0 s314 ms
Load timeN/A0.8 s
Memory usage0.0 GB10.4 GB
Memory %0%33%

HW Fit Score Breakdown

lfm2-24b-a2b

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

dolphin3:8b

Speed
42/50
TTFT
20/20
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

dolphin3:8b

Reasoning
12/20
Coding
13/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View lfm2-24b-a2b details | View dolphin3:8b 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