qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
59 vs 63
Hardware Fit
63 vs 62
Quality Score
58 vs 63
Hardware
qwen3.8-27b-mlx gemma4:12b
MachineMacBook ProMacBook Pro
CPUApple M5 MaxApple M1 Pro
Cores1810
RAM64 GB16 GB
GPUApple M5 MaxApple M1 Pro
OSmacOS 27.0macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx gemma4:12b
Tokens/sec18.315.3
First chunk4 ms1142 ms
TTFT530 ms30.0 s
Load timeN/A5.4 s
Memory usage38.5 GB7.6 GB
Memory %60%47%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
Quality
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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