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
google/gemma-4-12b-it-qat
LM-STUDIO GGUFgemma4 · 12B · Q4_0
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
88 vs 74
Hardware Fit
85 vs 46
Quality Score
89 vs 86
Hardware
huihui-qwen3.6-35b… google/gemma-4-12b…
MachineGigabyte Technology Co., Ltd. B550M AORUS PRODocker Container
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Gen Intel® Core™ i9-11900H
Cores1216
RAM47 GB15 GB
GPUAD106 [GeForce RTX 4060 Ti]TigerLake-H GT1 [UHD Graphics]
OScachyos rollingUbuntu 26.04 LTS
Archx64x64
Power Modelow-powerperformance
Performance
huihui-qwen3.6-35b… google/gemma-4-12b…
Tokens/sec37.75.0
First chunk18 ms64 ms
TTFT2.9 s5.5 s
Load timeN/A9.5 s
Memory usage26.1 GB0.0 GB
Memory %56%0%
HW Fit Score Breakdown
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
13/20
Memory
22/30
google/gemma-4-12b-it-qat
Speed
9/50
TTFT
7/20
Memory
30/30
Quality
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
google/gemma-4-12b-it-qat
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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