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

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Mar 5, 2026 · AMD Ryzen 9 8945HS

Global Score
71 vs 62
Hardware Fit
42 vs 91
Quality Score
84 vs 50

Hardware

qwen3:30b-a3b-inst… llama3.2:1b
MachineDell Inc. PowerEdge R820ASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UV
CPUIntel Xeon® E5-4620 0AMD Ryzen 9 8945HS
Cores6416
RAM256 GB15 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3:30b-a3b-inst… llama3.2:1b
Tokens/sec4.0170.2
First chunk2070 ms142 ms
TTFT2.1 s142 ms
Load time44.5 s3.2 s
Memory usage17.7 GB1.6 GB
Memory %7%11%

HW Fit Score Breakdown

qwen3:30b-a3b-instruct-…

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

llama3.2:1b

Speed
50/50
TTFT
20/20
Memory
21/30

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

llama3.2:1b

Reasoning
4/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
0/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

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