Back to leaderboard

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

qwen3-coder:30b-a3b-q8_0

OLLAMA GGUF

qwen3moe · 30.5B · Q8_0

Good

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
66 vs 78
Hardware Fit
23 vs 54
Quality Score
84 vs 88

Hardware

GPT-120B:120b qwen3-coder:30b-a3…
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLHP HP Pavilion Laptop 15-eh1xxx
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 5 5500U
Cores2012
RAM55 GB63 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUAMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 10 Enterprise LTSC 10.0.19044
Archarm64x64
Power Modebalancedbalanced

Performance

GPT-120B:120b qwen3-coder:30b-a3…
Tokens/sec16.88.0
First chunk11247 ms1468 ms
TTFT12.2 s1.5 s
Load time77.3 s114.5 s
Memory usage61.6 GB33.5 GB
Memory %113%53%

HW Fit Score Breakdown

GPT-120B:120b

Speed
21/50
TTFT
2/20
Memory
0/30

qwen3-coder:30b-a3b-q8_0

Speed
11/50
TTFT
19/20
Memory
24/30

Quality

GPT-120B:120b

Reasoning
16/20
Coding
19/20
Instruction
11/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-coder:30b-a3b-q8_0

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View GPT-120B:120b details | View qwen3-coder:30b-a3… details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest