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

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
65 vs 18
Hardware Fit
92 vs 53
Quality Score
54 vs 3

Hardware

qwen2.5:1.5b qwen3.5:0.8b
MachineiMacLENOVO 20L7CTO1WW
CPUIntel Core™ i7-4771Intel Core™ i5-8350U
Cores88
RAM32 GB23 GB
GPUNVIDIA GeForce GTX 780MKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 15.7.3Fedora Linux 43
Archx64x64
Power Modebalancedlow-power

Performance

qwen2.5:1.5b qwen3.5:0.8b
Tokens/sec19.69.4
First chunk690 ms799 ms
TTFT690 ms30.0 s
Load time21.4 s3.3 s
Memory usage1.0 GB1.9 GB
Memory %3%8%

HW Fit Score Breakdown

qwen2.5:1.5b

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

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
Memory
30/30

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
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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