Back to leaderboard

gpt-oss-20b

LM-STUDIO GGUF
Excellent

Mar 6, 2026 · Apple M4 Pro

lfm2-24b-a2b

LM-STUDIO GGUF
Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
95 vs 18
Hardware Fit
94 vs 59
Quality Score
95 vs 0

Hardware

gpt-oss-20b lfm2-24b-a2b
MachineMac miniMac mini
CPUApple M4 ProApple M4 Pro
Cores1414
RAM64 GB64 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

gpt-oss-20b lfm2-24b-a2b
Tokens/sec118.26.6
First chunk471 ms1025 ms
TTFT2.2 s1.0 s
Load timeN/AN/A
Memory usage11.3 GB0.0 GB
Memory %18%0%

HW Fit Score Breakdown

gpt-oss-20b

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

lfm2-24b-a2b

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

Quality

gpt-oss-20b

Reasoning
19/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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
View gpt-oss-20b details | View lfm2-24b-a2b 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