Back to leaderboard

qwen3:1.7b

OLLAMA GGUF

qwen3 · 2.0B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Gemma4-31B:31B

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Aug 18, 2026 · Intel Core™ Ultra X7 358H

Global Score
72 vs 76
Hardware Fit
92 vs 45
Quality Score
63 vs 89

Hardware

qwen3:1.7b Gemma4-31B:31B
MachineAZW GTR ProGMKtec NucBox EVO-T2S
CPUAMD RYZEN AI MAX+ 395Intel Core™ Ultra X7 358H
Cores3216
RAM125 GB64 GB
GPUAMD Radeon 8060SIntel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3:1.7b Gemma4-31B:31B
Tokens/sec120.73.8
First chunk93 ms3536 ms
TTFT1.5 s3.5 s
Load time2.5 s19.6 s
Memory usage5.8 GB19.9 GB
Memory %5%31%

HW Fit Score Breakdown

qwen3:1.7b

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

Gemma4-31B:31B

Speed
5/50
TTFT
10/20
Memory
30/30

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

Gemma4-31B:31B

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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