GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 25, 2026 · Intel Core™ Ultra X7 358H
qwen3-235b-a22b-t48-c8k:latest
OLLAMA GGUFqwen3moe · 235.1B · Q4_K_M
Aug 23, 2026 · Intel Xeon® E5-4650 v2
Global Score
68 vs 61
Hardware Fit
21 vs 31
Quality Score
88 vs 74
Hardware
GPT-120B:120b qwen3-235b-a22b-t4…
MachineGMKtec NucBox EVO-T2SDell Inc. PowerEdge R820
CPUIntel Core™ Ultra X7 358HIntel Xeon® E5-4650 v2
Cores1680
RAM64 GB256 GB
GPUIntel(R) Arc(TM) B390 GPUMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3-235b-a22b-t4…
Tokens/sec12.11.7
First chunk4392 ms3351 ms
TTFT8.7 s3.4 s
Load time80.1 s0.0 s
Memory usage61.0 GB134.2 GB
Memory %96%52%
HW Fit Score Breakdown
GPT-120B:120b
Speed
15/50
TTFT
4/20
Memory
2/30
qwen3-235b-a22b-t48-c8k…
Speed
1/50
TTFT
6/20
Memory
24/30
Quality
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-235b-a22b-t48-c8k…
Reasoning
19/20
Coding
11/20
Instruction
7/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak 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