Back to leaderboard

openai/gpt-oss-20b

LM-STUDIO MLX

gpt_oss · 20B · MXFP4

Not Rec.

Mar 19, 2026 · Apple M4

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Oct 31, 2026 · AMD RYZEN AI MAX+ 395

Global Score
77 vs 81
Hardware Fit
67 vs 84
Quality Score
81 vs 79

Hardware

openai/gpt-oss-20b google/gemma-4-e4b
MachineMac miniGMKtec EVO-X3
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB120 GB
GPUApple M4AMD Radeon(TM) 8060S Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced

Performance

openai/gpt-oss-20b google/gemma-4-e4b
Tokens/sec30.547.3
First chunk18 ms23 ms
TTFT30.0 s1.9 s
Load timeN/AN/A
Memory usage15.8 GB13.2 GB
Memory %66%11%

HW Fit Score Breakdown

openai/gpt-oss-20b

Speed
50/50
TTFT
0/20
Memory
17/30

google/gemma-4-e4b

Speed
44/50
TTFT
10/20
Memory
30/30

Quality

openai/gpt-oss-20b

Reasoning
19/20
Coding
11/20
Instruction
12/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View openai/gpt-oss-20b details | View google/gemma-4-e4b 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