phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
amd-olmo-1b-sft
LM-STUDIO GGUFolmo · 1B · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
Global Score
64 vs 44
Hardware Fit
100 vs 75
Quality Score
48 vs 30
Hardware
phi3:3.8b amd-olmo-1b-sft
MachineMacBook AirLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
phi3:3.8b amd-olmo-1b-sft
Tokens/sec42.09.2
First chunkN/A2093 ms
TTFT142 ms2.1 s
Load time1.1 sN/A
Memory usage16.0 GB0.7 GB
Memory %50%4%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
amd-olmo-1b-sft
Speed
30/50
TTFT
19/20
Memory
26/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
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