Back to leaderboard

qwen2.5-coder:0.5b

OLLAMA GGUF

qwen2 · 494.03M · Q4_K_M

Marginal

Nov 13, 2026 · Intel Core™ i5-4590T

qwen3.6:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Excellent

Apr 17, 2026 · AMD RYZEN AI MAX+ 395

Global Score
59 vs 88
Hardware Fit
100 vs 91
Quality Score
41 vs 87

Hardware

qwen2.5-coder:0.5b qwen3.6:35b-a3b
MachineFUJITSU ESPRIMO Q920AZW GTR Pro
CPUIntel Core™ i5-4590TAMD RYZEN AI MAX+ 395
Cores432
RAM16 GB125 GB
GPUIntel(R) HD Graphics 4600, Microsoft Remote Display AdapterRadeon 8060S
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

qwen2.5-coder:0.5b qwen3.6:35b-a3b
Tokens/sec43.743.3
First chunk290 ms291 ms
TTFT290 ms291 ms
Load time1.4 s6.2 s
Memory usage0.9 GB32.2 GB
Memory %6%26%

HW Fit Score Breakdown

qwen2.5-coder:0.5b

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

qwen3.6:35b-a3b

Speed
41/50
TTFT
20/20
Memory
30/30

Quality

qwen2.5-coder:0.5b

Reasoning
7/20
Coding
8/20
Instruction
10/20
Structured
10/15
Math
2/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Weak

qwen3.6:35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5-coder:0.5b details | View qwen3.6:35b-a3b 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