deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Mar 6, 2026 · Apple M4
neural-chat:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
66 vs 67
Hardware Fit
100 vs 96
Quality Score
51 vs 55
Hardware
deepseek-r1:1.5b neural-chat:7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-r1:1.5b neural-chat:7b
Tokens/sec85.422.5
First chunk115 msN/A
TTFT115 ms242 ms
Load time0.5 s0.4 s
Memory usage2.6 GB4.5 GB
Memory %8%14%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
50/50
TTFT
20/20
Memory
30/30
neural-chat:7b
Speed
36/50
TTFT
30/20
Memory
30/30
Quality
deepseek-r1:1.5b
Reasoning
14/20
Coding
4/20
Instruction
8/20
Structured
6/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
neural-chat:7b
Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak 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