qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
53 vs 88
Hardware Fit
72 vs 85
Quality Score
45 vs 89
Hardware
qwen3.5:9b huihui-qwen3.6-35b…
MachineMacBook ProGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M1 MaxAMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM32 GB47 GB
GPUApple M1 MaxAD106 [GeForce RTX 4060 Ti]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3.5:9b huihui-qwen3.6-35b…
Tokens/sec18.637.7
First chunk403 ms18 ms
TTFT10.2 s2.9 s
Load time4.3 sN/A
Memory usage9.1 GB26.1 GB
Memory %28%56%
HW Fit Score Breakdown
qwen3.5:9b
Speed
38/50
TTFT
4/20
Memory
30/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
13/20
Memory
22/30
Quality
qwen3.5:9b
Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
huihui-qwen3.6-35b-a3b-…
Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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