Back to leaderboard

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

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

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
86 vs 88
Hardware Fit
80 vs 90
Quality Score
89 vs 87

Hardware

gemma4:12b qwen/qwen3.6-35b-a3b
MachineASUSGMKtec EVO-X3
CPUIntel Gen Intel® Core™ i7-12700AMD RYZEN AI MAX+ 395
Cores2032
RAM30 GB120 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060AMD Radeon(TM) 8060S Graphics
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modelow-powerbalanced

Performance

gemma4:12b qwen/qwen3.6-35b-a3b
Tokens/sec74.449.0
First chunk152 ms44 ms
TTFT30.0 s334 ms
Load time0.0 s61.3 s
Memory usage0.8 GB59.8 GB
Memory %3%50%

HW Fit Score Breakdown

gemma4:12b

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

qwen/qwen3.6-35b-a3b

Speed
45/50
TTFT
20/20
Memory
25/30

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

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:12b details | View qwen/qwen3.6-35b-a3b 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