Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

qwen3:30b-a3b-instruct-2507-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
82 vs 71
Hardware Fit
81 vs 42
Quality Score
82 vs 84

Hardware

qwen3.5:9b qwen3:30b-a3b-inst…
MachineAZW GTR ProDell Inc. PowerEdge R820
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SIntel Xeon® E5-4620 0
Cores3264
RAM125 GB256 GB
GPUIntegrated / Apple SiliconMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSUbuntu 24.04.4 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5:9b qwen3:30b-a3b-inst…
Tokens/sec30.84.0
First chunk195 ms2070 ms
TTFT195 ms2.1 s
Load time6.8 s44.5 s
Memory usage18.8 GB17.7 GB
Memory %15%7%

HW Fit Score Breakdown

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
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
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest