Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Excellent

Oct 12, 2026 · AMD Ryzen 5 5500

google/gemma-4-12b-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
81 vs 92
Hardware Fit
98 vs 100
Quality Score
74 vs 89

Hardware

qwen3.5:4b google/gemma-4-12b…
MachineMicrosoft WSLMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 5 5500AMD Ryzen 7 9700X 8-Core Processor
Cores1216
RAM8 GB31 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeunknownbalanced

Performance

qwen3.5:4b google/gemma-4-12b…
Tokens/sec93.790.7
First chunk249 ms26 ms
TTFT249 ms127 ms
Load time10.1 sN/A
Memory usage2.9 GB6.7 GB
Memory %38%21%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
20/20
Memory
28/30

google/gemma-4-12b-qat

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

Quality

qwen3.5:4b

Reasoning
15/20
Coding
13/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

google/gemma-4-12b-qat

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b details | View google/gemma-4-12b… 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