gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp
LM-STUDIO GGUFqwen35 · 27B
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
91 vs 81
Hardware Fit
96 vs 64
Quality Score
89 vs 88
Hardware
gemma4:12b-mlx qwen3.8-27b-uncens…
MachineMacBook ProSystem manufacturer
CPUApple M2 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M2 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.5Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:12b-mlx qwen3.8-27b-uncens…
Tokens/sec24.711.7
First chunk610 ms50 ms
TTFT610 ms1.1 s
Load time3.6 sN/A
Memory usage7.1 GB15.8 GB
Memory %45%51%
HW Fit Score Breakdown
gemma4:12b-mlx
Speed
50/50
TTFT
20/20
Memory
26/30
qwen3.8-27b-uncensored-…
Speed
19/50
TTFT
20/20
Memory
25/30
Quality
gemma4:12b-mlx
Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.8-27b-uncensored-…
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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