Back to leaderboard

qwen3:1.7b

OLLAMA GGUF

qwen3 · 2.0B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Aug 22, 2026 · Apple M1 Pro

Global Score
72 vs 63
Hardware Fit
92 vs 62
Quality Score
63 vs 63

Hardware

qwen3:1.7b gemma4:12b
MachineAZW GTR ProMacBook Pro
CPUAMD RYZEN AI MAX+ 395Apple M1 Pro
Cores3210
RAM125 GB16 GB
GPUAMD Radeon 8060SApple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3:1.7b gemma4:12b
Tokens/sec120.715.3
First chunk93 ms1142 ms
TTFT1.5 s30.0 s
Load time2.5 s5.4 s
Memory usage5.8 GB7.6 GB
Memory %5%47%

HW Fit Score Breakdown

qwen3:1.7b

Speed
50/50
TTFT
12/20
Memory
30/30

gemma4:12b

Speed
36/50
TTFT
0/20
Memory
26/30

Quality

qwen3:1.7b

Reasoning
13/20
Coding
6/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

gemma4:12b

Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong

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