gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Sep 15, 2026 · Intel Core™ i5-14400F
qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Global Score
94 vs 77
Hardware Fit
97 vs 53
Quality Score
93 vs 87
Hardware
gpt-oss:20b qwen3.5:35b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4ASUS
CPUIntel Core™ i5-14400FIntel Core™ i5-14600KF
Cores1620
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 5060 TiNVIDIA GeForce RTX 4070 Ti SUPER
OSMicrosoft Windows 11 Professionnel 10.0.26200Microsoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
gpt-oss:20b qwen3.5:35b
Tokens/sec80.416.0
First chunk139 ms719 ms
TTFT1.6 s719 ms
Load time11.6 s17.8 s
Memory usage11.9 GB25.0 GB
Memory %37%79%
HW Fit Score Breakdown
gpt-oss:20b
Speed
50/50
TTFT
19/20
Memory
28/30
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
Quality
gpt-oss:20b
Reasoning
19/20
Coding
17/20
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
qwen3.5:35b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
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