qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Jun 25, 2026 · Cortex-A78AE
Global Score
77 vs 74
Hardware Fit
53 vs 99
Quality Score
87 vs 63
Hardware
qwen3.5:35b llama3.2:3b
MachineASUSNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i5-14600KFCortex-A78AE
Cores206
RAM32 GB7 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERIntegrated / Unknown
OSMicrosoft Windows 11 Famille 10.0.26200Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5:35b llama3.2:3b
Tokens/sec16.021.1
First chunk719 ms1032 ms
TTFT719 ms1.0 s
Load time17.8 s8.4 s
Memory usage25.0 GB2.4 GB
Memory %79%32%
HW Fit Score Breakdown
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
llama3.2:3b
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
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
llama3.2:3b
Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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