qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Aug 15, 2026 · Cortex-X925
gemma3:12b
OLLAMA GGUFgemma3 · 12.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
85 vs 80
Hardware Fit
79 vs 83
Quality Score
87 vs 78
Hardware
qwen3.8:27b gemma3:12b
MachineASUSTeK COMPUTER INC. GX10MacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen3.8:27b gemma3:12b
Tokens/sec27.412.7
First chunk593 msN/A
TTFT593 ms560 ms
Load time0.3 s2.8 s
Memory usage18.2 GB11.0 GB
Memory %15%34%
HW Fit Score Breakdown
qwen3.8:27b
Speed
29/50
TTFT
20/20
Memory
30/30
gemma3:12b
Speed
23/50
TTFT
30/20
Memory
30/30
Quality
qwen3.8:27b
Reasoning
18/20
Coding
17/20
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
gemma3:12b
Reasoning
14/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
7/15
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