Back to leaderboard

qwen3.5-9b-64k:latest

OLLAMA GGUF

qwen35 · 9.0B · Q4_K_M

Good

Oct 31, 2026 · Intel Gen Intel® Core™ i9-12900H

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
75 vs 83
Hardware Fit
68 vs 96
Quality Score
78 vs 78

Hardware

qwen3.5-9b-64k:lat… qwen3-vl:4b-instruct
MachineMicro-Star International Co., Ltd. Stealth GS77 12UHMac Studio
CPUIntel Gen Intel® Core™ i9-12900HApple M2 Max
Cores2012
RAM32 GB96 GB
GPUIntel(R) Iris(R) Xe Graphics, NVIDIA GeForce RTX 3080 Laptop GPUApple M2 Max
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-64k:lat… qwen3-vl:4b-instruct
Tokens/sec12.691.2
First chunk586 ms150 ms
TTFT586 ms150 ms
Load time15.0 s5.3 s
Memory usage8.1 GB42.5 GB
Memory %26%44%

HW Fit Score Breakdown

qwen3.5-9b-64k:latest

Speed
18/50
TTFT
20/20
Memory
30/30

qwen3-vl:4b-instruct

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

Quality

qwen3.5-9b-64k:latest

Reasoning
14/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate 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-64k:lat… 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