Back to leaderboard

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 16, 2026 · Intel Core™ i7-4771

qwen3.5-0.8b

LM-STUDIO GGUF

qwen35 · 0.8B · Q4_K_M

Marginal

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
65 vs 48
Hardware Fit
92 vs 61
Quality Score
54 vs 42

Hardware

qwen2.5:1.5b qwen3.5-0.8b
MachineiMacLENOVO 20BUS00700
CPUIntel Core™ i7-4771Intel Core™ i5-5300U
Cores84
RAM32 GB16 GB
GPUNVIDIA GeForce GTX 780MIntel(R) HD Graphics 5500
OSmacOS 15.7.3Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced

Performance

qwen2.5:1.5b qwen3.5-0.8b
Tokens/sec19.66.2
First chunk690 ms4461 ms
TTFT690 ms4.5 s
Load time21.4 sN/A
Memory usage1.0 GB0.7 GB
Memory %3%4%

HW Fit Score Breakdown

qwen2.5:1.5b

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

qwen3.5-0.8b

Speed
22/50
TTFT
12/20
Memory
27/30

Quality

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

qwen3.5-0.8b

Reasoning
10/20
Coding
2/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
View qwen2.5:1.5b details | View qwen3.5-0.8b 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