qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Xeon® E5-4620 0
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
Global Score
71 vs 87
Hardware Fit
42 vs 79
Quality Score
84 vs 90
Hardware
qwen3:30b-a3b-inst… gpt-oss:20b
MachineDell Inc. PowerEdge R820Mac mini
CPUIntel Xeon® E5-4620 0Apple M4
Cores6410
RAM256 GB24 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M4
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:30b-a3b-inst… gpt-oss:20b
Tokens/sec4.026.4
First chunk2070 ms505 ms
TTFT2.1 s6.7 s
Load time44.5 s10.5 s
Memory usage17.7 GB13.1 GB
Memory %7%55%
HW Fit Score Breakdown
qwen3:30b-a3b-instruct-…
Speed
3/50
TTFT
9/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
6/20
Memory
23/30
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
gpt-oss:20b
Reasoning
19/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
15/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest