codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
slim-rpcache-ornith-1.0-9b
LM-STUDIO GGUFqwen35 · 9B · BF16
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
76 vs 79
Hardware Fit
91 vs 78
Quality Score
69 vs 79
Hardware
codestral:latest slim-rpcache-ornit…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4ASUS
CPUIntel Core™ i5-14400FAMD Ryzen 7 7800X3D 8-Core Processor
Cores1616
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 5060 TiNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Professionnel 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedperformance
Performance
codestral:latest slim-rpcache-ornit…
Tokens/sec27.452.3
First chunk86 ms11 ms
TTFT86 ms177 ms
Load time7.2 sN/A
Memory usage12.6 GB25.6 GB
Memory %40%84%
HW Fit Score Breakdown
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
slim-rpcache-ornith-1.0…
Speed
50/50
TTFT
20/20
Memory
8/30
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
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