codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
67 vs 71
Hardware Fit
67 vs 100
Quality Score
67 vs 58
Hardware
codestral:22b phi4-mini:latest
MachineNVIDIA NVIDIA_DGX_SparkMacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced
Performance
codestral:22b phi4-mini:latest
Tokens/sec17.236.2
First chunk129 msN/A
TTFT129 ms190 ms
Load time11.6 s0.8 s
Memory usage18.9 GB8.3 GB
Memory %16%26%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
phi4-mini:latest
Speed
40/50
TTFT
30/20
Memory
30/30
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
phi4-mini:latest
Reasoning
12/20
Coding
10/20
Instruction
10/20
Structured
11/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate 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