codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
slim-rpcache-ornith-1.0-9b
LM-STUDIO GGUFqwen35 · 9B · BF16
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
67 vs 79
Hardware Fit
67 vs 78
Quality Score
67 vs 79
Hardware
codestral:22b slim-rpcache-ornit…
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925AMD Ryzen 7 7800X3D 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.4 LTScachyos rolling
Archarm64x64
Power Modeperformanceperformance
Performance
codestral:22b slim-rpcache-ornit…
Tokens/sec17.252.3
First chunk129 ms11 ms
TTFT129 ms177 ms
Load time11.6 sN/A
Memory usage18.9 GB25.6 GB
Memory %16%84%
HW Fit Score Breakdown
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
slim-rpcache-ornith-1.0…
Speed
50/50
TTFT
20/20
Memory
8/30
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
slim-rpcache-ornith-1.0…
Reasoning
16/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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