codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
qwen3:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
67 vs 86
Hardware Fit
67 vs 98
Quality Score
67 vs 81
Hardware
codestral:22b qwen3:30b
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925Intel Core™ Ultra 9 285K
Cores2024
RAM122 GB47 GB
GPUDevice 2e12NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
codestral:22b qwen3:30b
Tokens/sec17.2204.8
First chunk129 ms96 ms
TTFT129 ms674 ms
Load time11.6 s5.2 s
Memory usage18.9 GB20.5 GB
Memory %16%43%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
qwen3:30b
Speed
50/50
TTFT
20/20
Memory
28/30
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
qwen3:30b
Reasoning
16/20
Coding
12/20
Instruction
17/20
Structured
12/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong 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