qwen/qwen3.8-27b
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Aug 19, 2026 · Apple M4 Max
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Jun 25, 2026 · Apple M4 Pro
Global Score
83 vs 79
Hardware Fit
68 vs 98
Quality Score
90 vs 71
Hardware
qwen/qwen3.8-27b ministral-3:8b
MachineMacBook ProMac mini
CPUApple M4 MaxApple M4 Pro
Cores1612
RAM128 GB24 GB
GPUApple M4 MaxApple M4 Pro
OSmacOS 26.5.2macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen/qwen3.8-27b ministral-3:8b
Tokens/sec27.641.4
First chunk10 ms257 ms
TTFT4.6 s257 ms
Load timeN/A5.2 s
Memory usage21.0 GB9.0 GB
Memory %16%38%
HW Fit Score Breakdown
qwen/qwen3.8-27b
Speed
32/50
TTFT
6/20
Memory
30/30
ministral-3:8b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
qwen/qwen3.8-27b
Reasoning
19/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
12/20
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