GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Xeon® E5-4620 0
Global Score
79 vs 71
Hardware Fit
47 vs 42
Quality Score
93 vs 84
Hardware
GPT-120B:120b qwen3:30b-a3b-inst…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCDell Inc. PowerEdge R820
CPUIntel Core™ i7-14700FIntel Xeon® E5-4620 0
Cores2864
RAM128 GB256 GB
GPUNVIDIA GeForce RTX 5080Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3:30b-a3b-inst…
Tokens/sec18.24.0
First chunk1719 ms2070 ms
TTFT3.9 s2.1 s
Load time50.9 s44.5 s
Memory usage61.5 GB17.7 GB
Memory %48%7%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3:30b-a3b-instruct-…
Speed
3/50
TTFT
9/20
Memory
30/30
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
qwen3:30b-a3b-instruct-…
Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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