qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Xeon® E5-4620 0
phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
71 vs 28
Hardware Fit
42 vs 66
Quality Score
84 vs 11
Hardware
qwen3:30b-a3b-inst… phi-1_5
MachineDell Inc. PowerEdge R820LENOVO 20BUS00700
CPUIntel Xeon® E5-4620 0Intel Core™ i5-5300U
Cores644
RAM256 GB16 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterIntel(R) HD Graphics 5500
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
qwen3:30b-a3b-inst… phi-1_5
Tokens/sec4.06.9
First chunk2070 ms3040 ms
TTFT2.1 s3.0 s
Load time44.5 sN/A
Memory usage17.7 GB1.4 GB
Memory %7%9%
HW Fit Score Breakdown
qwen3:30b-a3b-instruct-…
Speed
3/50
TTFT
9/20
Memory
30/30
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
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
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest