Back to leaderboard

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 16, 2026 · Intel Core™ i7-4771

Global Score
77 vs 65
Hardware Fit
53 vs 92
Quality Score
87 vs 54

Hardware

qwen3.5:35b qwen2.5:1.5b
MachineASUSiMac
CPUIntel Core™ i5-14600KFIntel Core™ i7-4771
Cores208
RAM32 GB32 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERNVIDIA GeForce GTX 780M
OSMicrosoft Windows 11 Famille 10.0.26200macOS 15.7.3
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b qwen2.5:1.5b
Tokens/sec16.019.6
First chunk719 ms690 ms
TTFT719 ms690 ms
Load time17.8 s21.4 s
Memory usage25.0 GB1.0 GB
Memory %79%3%

HW Fit Score Breakdown

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

qwen2.5:1.5b

Speed
42/50
TTFT
20/20
Memory
30/30

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

qwen2.5:1.5b

Reasoning
8/20
Coding
9/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
View qwen3.5:35b details | View qwen2.5:1.5b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest