GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
devstral:24b
OLLAMA GGUFllama · 23.6B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
79 vs 80
Hardware Fit
47 vs 79
Quality Score
93 vs 80
Hardware
GPT-120B:120b devstral:24b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUIntel Core™ i7-14700FIntel Core™ i5-14400F
Cores2816
RAM128 GB32 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b devstral:24b
Tokens/sec18.220.2
First chunk1719 ms137 ms
TTFT3.9 s137 ms
Load time50.9 s9.6 s
Memory usage61.5 GB14.2 GB
Memory %48%45%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
devstral:24b
Speed
33/50
TTFT
20/20
Memory
26/30
Quality
GPT-120B:120b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
devstral:24b
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
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