qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 2, 2026 · Apple M4
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
65 vs 72
Hardware Fit
99 vs 71
Quality Score
51 vs 72
Hardware
qwen3.5:0.8b ministral-3:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:0.8b ministral-3:8b
Tokens/sec48.219.8
First chunkN/A269 ms
TTFT195 ms269 ms
Load time1.0 s10.7 s
Memory usage2.5 GB13.7 GB
Memory %8%86%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
40/50
TTFT
30/20
Memory
29/30
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
Quality
qwen3.5:0.8b
Reasoning
9/20
Coding
6/20
Instruction
11/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong 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