deepseek-r1:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 6, 2026 · Apple M4
qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 8bit
Mar 3, 2026 · Apple M4
Global Score
77 vs 60
Hardware Fit
94 vs 96
Quality Score
70 vs 44
Hardware
deepseek-r1:7b qwen3.5-0.8b-mlx
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-r1:7b qwen3.5-0.8b-mlx
Tokens/sec22.2108.0
First chunk285 ms2568 ms
TTFT285 ms2.6 s
Load time0.8 sN/A
Memory usage7.6 GB1.0 GB
Memory %24%3%
HW Fit Score Breakdown
deepseek-r1:7b
Speed
44/50
TTFT
20/20
Memory
30/30
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
16/20
Memory
30/30
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
qwen3.5-0.8b-mlx
Reasoning
10/20
Coding
3/20
Instruction
11/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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