gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
qwen3-next-80b-t48:latest
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Jul 31, 2026 · Intel Xeon® E5-4620 0
Global Score
88 vs 70
Hardware Fit
86 vs 39
Quality Score
89 vs 83
Hardware
gemma4:12b-it-qat qwen3-next-80b-t48…
MachineMac miniDell Inc. PowerEdge R820
CPUApple M4 ProIntel Xeon® E5-4620 0
Cores1264
RAM24 GB256 GB
GPUApple M4 ProMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSmacOS 15.6.1Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b-it-qat qwen3-next-80b-t48…
Tokens/sec30.03.0
First chunk686 ms3265 ms
TTFT7.1 s3.3 s
Load time5.4 s82.1 s
Memory usage7.1 GB46.9 GB
Memory %30%18%
HW Fit Score Breakdown
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
qwen3-next-80b-t48:latest
Speed
3/50
TTFT
6/20
Memory
30/30
Quality
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-next-80b-t48:latest
Reasoning
18/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak 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