gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jul 4, 2026 · Apple M2 Pro
amd-olmo-1b-sft
LM-STUDIO GGUFolmo · 1B · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
Global Score
89 vs 44
Hardware Fit
88 vs 75
Quality Score
89 vs 30
Hardware
gemma4:12b amd-olmo-1b-sft
MachineMacBook ProLENOVO 20BUS00700
CPUApple M2 ProIntel Core™ i5-5300U
Cores104
RAM16 GB16 GB
GPUApple M2 ProIntel(R) HD Graphics 5500
OSmacOS 26.5Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b amd-olmo-1b-sft
Tokens/sec18.49.2
First chunk758 ms2093 ms
TTFT758 ms2.1 s
Load time0.3 sN/A
Memory usage7.5 GB0.7 GB
Memory %47%4%
HW Fit Score Breakdown
gemma4:12b
Speed
42/50
TTFT
20/20
Memory
26/30
amd-olmo-1b-sft
Speed
30/50
TTFT
19/20
Memory
26/30
Quality
gemma4:12b
Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
amd-olmo-1b-sft
Reasoning
4/20
Coding
2/20
Instruction
11/20
Structured
9/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Poor
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