Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.2B · Q4_K_M

Marginal

Oct 12, 2026 · AMD Ryzen 5 5500

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
50 vs 72
Hardware Fit
93 vs 77
Quality Score
31 vs 70

Hardware

qwen3.5:4b llama3.1:8b
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M1 Pro
Cores1210
RAM8 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 26.6.2
Archx64arm64
Power Modeunknownbalanced

Performance

qwen3.5:4b llama3.1:8b
Tokens/sec92.621.5
First chunk323 ms368 ms
TTFT2.8 s368 ms
Load time9.0 s6.9 s
Memory usage2.9 GB12.9 GB
Memory %38%81%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
15/20
Memory
28/30

llama3.1:8b

Speed
47/50
TTFT
20/20
Memory
10/30

Quality

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
12/15
Multilingual
0/10
Reasoning: Strong Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

llama3.1:8b

Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:4b details | View llama3.1:8b 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