gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
Global Score
94 vs 83
Hardware Fit
91 vs 70
Quality Score
95 vs 89
Hardware
gpt-oss:20b qwen3:30b-a3b-inst…
MachineFramework Desktop (AMD Ryzen AI Max 300 Series)Micro-Star International Co., Ltd. MS-7D98
CPUAMD RYZEN AI MAX+ 395Intel Core™ i9-14900K
Cores3232
RAM64 GB128 GB
GPUAMD Radeon(TM) 8060S GraphicsIntel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSMicrosoft Windows 11 Pro for Workstations 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b qwen3:30b-a3b-inst…
Tokens/sec48.021.2
First chunk357 ms468 ms
TTFT2.3 s468 ms
Load time0.2 s9.6 s
Memory usage16.4 GB17.7 GB
Memory %26%14%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
Memory
30/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:30b-a3b-instruct-…
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
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