granite4.2:3b
OLLAMA GGUFgranite · 3.7B · Q4_K_M
Aug 29, 2026 · Apple M1 Pro
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
59 vs 67
Hardware Fit
80 vs 67
Quality Score
50 vs 67
Hardware
granite4.2:3b codestral:22b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
granite4.2:3b codestral:22b
Tokens/sec46.317.2
First chunk167 ms129 ms
TTFT167 ms129 ms
Load time6.3 s11.6 s
Memory usage12.7 GB18.9 GB
Memory %79%16%
HW Fit Score Breakdown
granite4.2:3b
Speed
50/50
TTFT
20/20
Memory
10/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
granite4.2:3b
Reasoning
18/20
Coding
10/20
Instruction
5/20
Structured
0/15
Math
15/15
Multilingual
2/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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
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