gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
codestral:latest
OLLAMA GGUFllama · 22.2B · Q4_0
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
94 vs 76
Hardware Fit
91 vs 91
Quality Score
95 vs 69
Hardware
gpt-oss:20b codestral:latest
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)Gigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD RYZEN AI MAX+ 395Intel Core™ i5-14400F
Cores3216
RAM64 GB32 GB
GPUAMD Radeon(TM) 8060S GraphicsNVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b codestral:latest
Tokens/sec48.027.4
First chunk357 ms86 ms
TTFT2.3 s86 ms
Load time0.2 s7.2 s
Memory usage16.4 GB12.6 GB
Memory %26%40%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
codestral:latest
Speed
43/50
TTFT
20/20
Memory
28/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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
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