qwen3.5:122b-a10b
OLLAMA GGUFqwen35moe · 125.1B · Q4_K_M
Mar 12, 2026 · AMD RYZEN AI MAX+ 395
GPT-OSS-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
80 vs 93
Hardware Fit
52 vs 92
Quality Score
92 vs 93
Hardware
qwen3.5:122b-a10b GPT-OSS-20B:20b
MachineAZW GTR ProHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUAMD RYZEN AI MAX+ 395Intel Core™ i7-14700F
Cores3228
RAM125 GB128 GB
GPURadeon 8060SNVIDIA GeForce RTX 5080
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
qwen3.5:122b-a10b GPT-OSS-20B:20b
Tokens/sec19.1178.6
First chunk467 ms695 ms
TTFT467 ms1.4 s
Load time30.0 s31.2 s
Memory usage89.3 GB11.9 GB
Memory %72%9%
HW Fit Score Breakdown
qwen3.5:122b-a10b
Speed
18/50
TTFT
20/20
Memory
14/30
GPT-OSS-20B:20b
Speed
50/50
TTFT
12/20
Memory
30/30
Quality
qwen3.5:122b-a10b
Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
GPT-OSS-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
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