Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Apr 28, 2026 · Intel Xeon® Gold 6230

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
80 vs 71
Hardware Fit
85 vs 42
Quality Score
78 vs 84

Hardware

qwen3:8b qwen3:30b-a3b-inst…
MachineHP HP Z8 G4 WorkstationDell Inc. PowerEdge R820
CPUIntel Xeon® Gold 6230Intel Xeon® E5-4620 0
Cores8064
RAM252 GB256 GB
GPUTU104GL [Quadro RTX 5000]Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSUbuntu 24.04.4 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3:8b qwen3:30b-a3b-inst…
Tokens/sec65.14.0
First chunk289 ms2070 ms
TTFT4.2 s2.1 s
Load time4.6 s44.5 s
Memory usage5.6 GB17.7 GB
Memory %2%7%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
5/20
Memory
30/30

qwen3:30b-a3b-instruct-…

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

Quality

qwen3:8b

Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong 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