codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
67 vs 81
Hardware Fit
67 vs 100
Quality Score
67 vs 73
Hardware
codestral:22b llama3.1:8b
MachineNVIDIA NVIDIA_DGX_SparkGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUCortex-X925Intel Core™ i5-14400F
Cores2016
RAM122 GB32 GB
GPUDevice 2e12NVIDIA GeForce RTX 5060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
codestral:22b llama3.1:8b
Tokens/sec17.270.2
First chunk129 ms58 ms
TTFT129 ms58 ms
Load time11.6 s4.1 s
Memory usage18.9 GB4.9 GB
Memory %16%15%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
llama3.1:8b
Speed
50/50
TTFT
20/20
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
llama3.1:8b
Reasoning
12/20
Coding
18/20
Instruction
15/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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