qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jun 26, 2026 · Cortex-X925
Global Score
82 vs 93
Hardware Fit
81 vs 87
Quality Score
82 vs 95
Hardware
qwen3.5:9b gpt-oss:20b
MachineAZW GTR ProNVIDIA NVIDIA_DGX_Spark
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SCortex-X925
Cores3220
RAM125 GB122 GB
GPUIntegrated / Apple SiliconDevice 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance
Performance
qwen3.5:9b gpt-oss:20b
Tokens/sec30.860.5
First chunk195 ms527 ms
TTFT195 ms3.1 s
Load time6.8 s14.0 s
Memory usage18.8 GB12.0 GB
Memory %15%10%
HW Fit Score Breakdown
qwen3.5:9b
Speed
31/50
TTFT
20/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
7/20
Memory
30/30
Quality
qwen3.5:9b
Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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