qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Aug 22, 2026 · Intel Xeon® E5-2637 v3
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
90 vs 94
Hardware Fit
98 vs 97
Quality Score
86 vs 93
Hardware
qwen3.5:35b-a3b-q4… gpt-oss:20b
MachineDell Inc. Precision Tower 7910Gigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUIntel Xeon® E5-2637 v3Intel Core™ i5-14400F
Cores1616
RAM96 GB32 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060NVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
qwen3.5:35b-a3b-q4… gpt-oss:20b
Tokens/sec48.480.4
First chunk1085 ms139 ms
TTFT1.1 s1.6 s
Load time22.2 s11.6 s
Memory usage22.9 GB11.9 GB
Memory %24%37%
HW Fit Score Breakdown
qwen3.5:35b-a3b-q4_K_M
Speed
50/50
TTFT
18/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
19/20
Memory
28/30
Quality
qwen3.5:35b-a3b-q4_K_M
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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
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