Back to leaderboard

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

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Not Rec.

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
71 vs 65
Hardware Fit
42 vs 73
Quality Score
84 vs 62

Hardware

qwen3:30b-a3b-inst… qwen3.5:4b
MachineDell Inc. PowerEdge R820AZW GTR Pro
CPUIntel Xeon® E5-4620 0AMD RYZEN AI MAX+ 395
Cores6432
RAM256 GB125 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterAMD Radeon 8060S
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

qwen3:30b-a3b-inst… qwen3.5:4b
Tokens/sec4.045.7
First chunk2070 ms180 ms
TTFT2.1 s30.0 s
Load time44.5 s5.3 s
Memory usage17.7 GB16.2 GB
Memory %7%13%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

Speed
3/50
TTFT
9/20
Memory
30/30

qwen3.5:4b

Speed
43/50
TTFT
0/20
Memory
30/30

Quality

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

qwen3.5:4b

Reasoning
17/20
Coding
1/20
Instruction
13/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate 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