Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score
57 vs 47
Hardware Fit
61 vs 53
Quality Score
55 vs 45

Hardware

qwen3.5:9b qwen3:4b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB32 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerunknown

Performance

qwen3.5:9b qwen3:4b
Tokens/sec30.311.3
First chunk205 msN/A
TTFT8.7 s9.2 s
Load time5.6 s0.1 s
Memory usage18.8 GB7.2 GB
Memory %15%23%

HW Fit Score Breakdown

qwen3.5:9b

Speed
30/50
TTFT
1/20
Memory
30/30

qwen3:4b

Speed
17/50
TTFT
6/20
Memory
30/30

Quality

qwen3.5:9b

Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

qwen3:4b

Reasoning
4/20
Coding
6/20
Instruction
8/20
Structured
6/15
Math
12/15
Multilingual
9/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong
View qwen3.5:9b details | View qwen3:4b 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