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 )

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Oct 11, 2026 · AMD Ryzen 5 5500

Global Score
66 vs 74
Hardware Fit
23 vs 100
Quality Score
84 vs 63

Hardware

GPT-120B:120b qwen3:0.6b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMicrosoft WSL
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 5 5500
Cores2012
RAM55 GB8 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUIntegrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.28000Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown

Performance

GPT-120B:120b qwen3:0.6b
Tokens/sec16.8249.5
First chunk11247 ms80 ms
TTFT12.2 s659 ms
Load time77.3 s6.3 s
Memory usage61.6 GB0.9 GB
Memory %113%11%

HW Fit Score Breakdown

GPT-120B:120b

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

qwen3:0.6b

Speed
50/50
TTFT
20/20
Memory
30/30

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

qwen3:0.6b

Reasoning
13/20
Coding
6/20
Instruction
12/20
Structured
13/15
Math
12/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
View GPT-120B:120b details | View qwen3:0.6b 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