gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
83 vs 76
Hardware Fit
64 vs 51
Quality Score
91 vs 87
Hardware
gpt-oss:120b qwen3-coder:latest
MachineNVIDIA NVIDIA_DGX_SparkDell Inc. Inspiron 15 3530
CPUCortex-X925Intel Gen Intel® Core™ i7-1355U
Cores2012
RAM122 GB31 GB
GPUDevice 2e12Raptor Lake-P [Iris Xe Graphics]
OSUbuntu 24.04.5 LTScachyos rolling
Archarm64x64
Power Modeperformancelow-power
Performance
gpt-oss:120b qwen3-coder:latest
Tokens/sec28.67.6
First chunk422 ms2037 ms
TTFT2.5 s2.0 s
Load time9.9 s8.7 s
Memory usage60.1 GB18.9 GB
Memory %49%61%
HW Fit Score Breakdown
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
Quality
gpt-oss:120b
Reasoning
19/20
Coding
19/20
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
qwen3-coder:latest
Reasoning
16/20
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
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