gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 10, 2026 · Apple M4
deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-6500
Global Score
83 vs 66
Hardware Fit
65 vs 63
Quality Score
90 vs 67
Hardware
gpt-oss:20b deepseek-r1:7b
MachineMac miniGigabyte Technology Co., Ltd. H170M-D3H
CPUApple M4Intel Core™ i5-6500
Cores104
RAM24 GB16 GB
GPUApple M4GP104 [GeForce GTX 1070]
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
gpt-oss:20b deepseek-r1:7b
Tokens/sec17.135.6
First chunk705 ms224 ms
TTFT10.2 s7.5 s
Load time23.1 s7.7 s
Memory usage13.1 GB4.6 GB
Memory %55%29%
HW Fit Score Breakdown
gpt-oss:20b
Speed
37/50
TTFT
5/20
Memory
23/30
deepseek-r1:7b
Speed
50/50
TTFT
7/20
Memory
6/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
deepseek-r1:7b
Reasoning
16/20
Coding
10/20
Instruction
9/20
Structured
10/15
Math
14/15
Multilingual
8/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Adequate 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