codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
Global Score
76 vs 63
Hardware Fit
91 vs 62
Quality Score
69 vs 63
Hardware
codestral:latest gemma4:12b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4MacBook Pro
CPUIntel Core™ i5-14400FApple M1 Pro
Cores1610
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 5060 TiApple M1 Pro
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
codestral:latest gemma4:12b
Tokens/sec27.415.3
First chunk86 ms1142 ms
TTFT86 ms30.0 s
Load time7.2 s5.4 s
Memory usage12.6 GB7.6 GB
Memory %40%47%
HW Fit Score Breakdown
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
Quality
codestral:latest
Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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