Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
82 vs 83
Hardware Fit
81 vs 96
Quality Score
82 vs 78

Hardware

qwen3.5:9b qwen3-vl:4b-instruct
MachineAZW GTR ProMac Studio
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SApple M2 Max
Cores3212
RAM125 GB96 GB
GPUIntegrated / Apple SiliconApple M2 Max
OSUbuntu 24.04.4 LTSmacOS 26.1
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5:9b qwen3-vl:4b-instruct
Tokens/sec30.891.2
First chunk195 ms150 ms
TTFT195 ms150 ms
Load time6.8 s5.3 s
Memory usage18.8 GB42.5 GB
Memory %15%44%

HW Fit Score Breakdown

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

Quality

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:9b details | View qwen3-vl:4b-instruct 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