qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
Global Score
82 vs 83
Hardware Fit
81 vs 70
Quality Score
82 vs 89
Hardware
qwen3.5:9b qwen3:30b-a3b-inst…
MachineAZW GTR ProMicro-Star International Co., Ltd. MS-7D98
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SIntel Core™ i9-14900K
Cores3232
RAM125 GB128 GB
GPUIntegrated / Apple SiliconIntel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
qwen3.5:9b qwen3:30b-a3b-inst…
Tokens/sec30.821.2
First chunk195 ms468 ms
TTFT195 ms468 ms
Load time6.8 s9.6 s
Memory usage18.8 GB17.7 GB
Memory %15%14%
HW Fit Score Breakdown
qwen3.5:9b
Speed
31/50
TTFT
20/20
Memory
30/30
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
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
qwen3:30b-a3b-instruct-…
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
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