deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 6, 2026 · Apple M4
gemma-3-1b-it
LM-STUDIO GGUFgemma3 · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
77 vs 59
Hardware Fit
94 vs 76
Quality Score
70 vs 52
Hardware
deepseek-r1:7b gemma-3-1b-it
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
deepseek-r1:7b gemma-3-1b-it
Tokens/sec22.28.7
First chunk285 ms2078 ms
TTFT285 ms2.1 s
Load time0.8 sN/A
Memory usage7.6 GB0.8 GB
Memory %24%5%
HW Fit Score Breakdown
deepseek-r1:7b
Speed
44/50
TTFT
20/20
Memory
30/30
gemma-3-1b-it
Speed
29/50
TTFT
19/20
Memory
28/30
Quality
deepseek-r1:7b
Reasoning
14/20
Coding
12/20
Instruction
10/20
Structured
12/15
Math
15/15
Multilingual
7/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
gemma-3-1b-it
Reasoning
4/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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