qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
62 vs 57
Hardware Fit
100 vs 61
Quality Score
46 vs 55
Hardware
qwen3.5:0.8b qwen3.5:9b
MachineMacBook ProAZW GTR Pro
CPUApple M1 MaxAMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M1 MaxAMD Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3.5:0.8b qwen3.5:9b
Tokens/sec65.830.3
First chunk230 ms205 ms
TTFT230 ms8.7 s
Load time1.5 s5.6 s
Memory usage2.6 GB18.8 GB
Memory %8%15%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:9b
Speed
30/50
TTFT
1/20
Memory
30/30
Quality
qwen3.5:0.8b
Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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
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