Back to leaderboard

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 5, 2026 · Apple M1 Max

qwen2.5vl:7b

OLLAMA GGUF

qwen25vl · 8.3B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
62 vs 83
Hardware Fit
100 vs 100
Quality Score
46 vs 75

Hardware

qwen3.5:0.8b qwen2.5vl:7b
MachineMacBook ProGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M1 MaxIntel Core™ i5-14400F
Cores1016
RAM32 GB32 GB
GPUApple M1 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.3Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:0.8b qwen2.5vl:7b
Tokens/sec65.873.9
First chunk230 ms53 ms
TTFT230 ms53 ms
Load time1.5 s5.3 s
Memory usage2.6 GB5.1 GB
Memory %8%16%

HW Fit Score Breakdown

qwen3.5:0.8b

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

qwen2.5vl:7b

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

Quality

qwen3.5:0.8b

Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

qwen2.5vl:7b

Reasoning
16/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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