qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M4
Global Score
57 vs 48
Hardware Fit
61 vs 77
Quality Score
55 vs 35
Hardware
qwen3.5:9b qwen3.5:4b
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395Apple M4
Cores3210
RAM125 GB16 GB
GPUAMD Radeon 8060SApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
qwen3.5:9b qwen3.5:4b
Tokens/sec30.318.9
First chunk205 ms316 ms
TTFT8.7 s13.0 s
Load time5.6 s3.7 s
Memory usage18.8 GB5.9 GB
Memory %15%37%
HW Fit Score Breakdown
qwen3.5:9b
Speed
30/50
TTFT
1/20
Memory
30/30
qwen3.5:4b
Speed
43/50
TTFT
4/20
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
qwen3.5:4b
Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest