qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
57 vs 83
Hardware Fit
61 vs 64
Quality Score
55 vs 91
Hardware
qwen3.5:9b gpt-oss:120b
MachineAZW GTR ProNVIDIA NVIDIA_DGX_Spark
CPUAMD RYZEN AI MAX+ 395Cortex-X925
Cores3220
RAM125 GB122 GB
GPUAMD Radeon 8060SDevice 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.5 LTS
Archx64arm64
Power Modelow-powerperformance
Performance
qwen3.5:9b gpt-oss:120b
Tokens/sec30.328.6
First chunk205 ms422 ms
TTFT8.7 s2.5 s
Load time5.6 s9.9 s
Memory usage18.8 GB60.1 GB
Memory %15%49%
HW Fit Score Breakdown
qwen3.5:9b
Speed
30/50
TTFT
1/20
Memory
30/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
Quality
qwen3.5:9b
Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
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
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