codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
67 vs 63
Hardware Fit
67 vs 62
Quality Score
67 vs 63
Hardware
codestral:22b gemma4:12b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
codestral:22b gemma4:12b
Tokens/sec17.215.3
First chunk129 ms1142 ms
TTFT129 ms30.0 s
Load time11.6 s5.4 s
Memory usage18.9 GB7.6 GB
Memory %16%47%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
Quality
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
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