qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
82 vs 59
Hardware Fit
81 vs 100
Quality Score
82 vs 41
Hardware
qwen3.5:9b phi:2.7b
MachineAZW GTR ProMacBook Air
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SApple M4
Cores3210
RAM125 GB32 GB
GPUIntegrated / Apple SiliconApple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
qwen3.5:9b phi:2.7b
Tokens/sec30.856.6
First chunk195 msN/A
TTFT195 ms110 ms
Load time6.8 s0.4 s
Memory usage18.8 GB2.2 GB
Memory %15%7%
HW Fit Score Breakdown
qwen3.5:9b
Speed
31/50
TTFT
20/20
Memory
30/30
phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
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
phi:2.7b
Reasoning
7/20
Coding
4/20
Instruction
9/20
Structured
11/15
Math
8/15
Multilingual
2/10
Reasoning: Weak Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Poor
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