Back to leaderboard

qwen3:32b

OLLAMA GGUF

qwen3 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

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
79 vs 71
Hardware Fit
59 vs 42
Quality Score
88 vs 84

Hardware

qwen3:32b qwen3:30b-a3b-inst…
MachineNVIDIA NVIDIA_DGX_SparkDell Inc. PowerEdge R820
CPUCortex-X925Intel Xeon® E5-4620 0
Cores2064
RAM122 GB256 GB
GPUDevice 2e12Microsoft Remote Display Adapter, Microsoft Basic Display Adapter
OSUbuntu 24.04.4 LTSMicrosoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modeperformancebalanced

Performance

qwen3:32b qwen3:30b-a3b-inst…
Tokens/sec9.74.0
First chunk324 ms2070 ms
TTFT324 ms2.1 s
Load time24.5 s44.5 s
Memory usage26.8 GB17.7 GB
Memory %22%7%

HW Fit Score Breakdown

qwen3:32b

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

qwen3:30b-a3b-instruct-…

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

Quality

qwen3:32b

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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