gemma4:12b-fast
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
85 vs 88
Hardware Fit
80 vs 85
Quality Score
87 vs 89
Hardware
gemma4:12b-fast huihui-qwen3.6-35b…
MachineASUSGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Gen Intel® Core™ i7-12700AMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM30 GB47 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060AD106 [GeForce RTX 4060 Ti]
OSUbuntu 26.04.1 LTScachyos rolling
Archx64x64
Power Modelow-powerlow-power
Performance
gemma4:12b-fast huihui-qwen3.6-35b…
Tokens/sec75.937.7
First chunk169 ms18 ms
TTFT30.0 s2.9 s
Load time8.4 sN/A
Memory usage1.3 GB26.1 GB
Memory %5%56%
HW Fit Score Breakdown
gemma4:12b-fast
Speed
50/50
TTFT
0/20
Memory
30/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
13/20
Memory
22/30
Quality
gemma4:12b-fast
Reasoning
18/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
huihui-qwen3.6-35b-a3b-…
Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest