Back to leaderboard

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700

qwen3.5-9b@q5_k_xl

LM-STUDIO GGUF

qwen35 · 9B · Q5_K_XL

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
86 vs 73
Hardware Fit
80 vs 47
Quality Score
89 vs 84

Hardware

gemma4:12b qwen3.5-9b@q5_k_xl
MachineASUSDocker Container
CPUIntel Gen Intel® Core™ i7-12700Intel Gen Intel® Core™ i9-11900H
Cores2016
RAM30 GB15 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060TigerLake-H GT1 [UHD Graphics]
OSUbuntu 26.04.1 LTSUbuntu 26.04 LTS
Archx64x64
Power Modelow-powerperformance

Performance

gemma4:12b qwen3.5-9b@q5_k_xl
Tokens/sec74.45.6
First chunk152 ms19 ms
TTFT30.0 s5.6 s
Load time0.0 s12.5 s
Memory usage0.8 GB0.0 GB
Memory %3%0%

HW Fit Score Breakdown

gemma4:12b

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

qwen3.5-9b@q5_k_xl

Speed
10/50
TTFT
7/20
Memory
30/30

Quality

gemma4:12b

Reasoning
18/20
Coding
15/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-9b@q5_k_xl

Reasoning
15/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View gemma4:12b details | View qwen3.5-9b@q5_k_xl 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