GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex-mtp
LM-STUDIO GGUFqwen35moe · 35B
Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
79 vs 89
Hardware Fit
47 vs 90
Quality Score
93 vs 88
Hardware
GPT-120B:120b qwen3.6-35b-a3b-cl…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUIntel Core™ i7-14700FAMD Ryzen 5 5600X 6-Core Processor
Cores2812
RAM128 GB47 GB
GPUNVIDIA GeForce RTX 5080AD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Enterprise 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
GPT-120B:120b qwen3.6-35b-a3b-cl…
Tokens/sec18.242.2
First chunk1719 ms40 ms
TTFT3.9 s2.7 s
Load time50.9 sN/A
Memory usage61.5 GB21.9 GB
Memory %48%47%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.6-35b-a3b-claude-…
Speed
50/50
TTFT
14/20
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
qwen3.6-35b-a3b-claude-…
Reasoning
19/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
15/15
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