qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
Global Score
61 vs 83
Hardware Fit
85 vs 70
Quality Score
51 vs 89
Hardware
qwen3:0.6b qwen3:30b-a3b-inst…
MachineLENOVO 20L7CTO1WWMicro-Star International Co., Ltd. MS-7D98
CPUIntel Core™ i5-8350UIntel Core™ i9-14900K
Cores832
RAM23 GB128 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
qwen3:0.6b qwen3:30b-a3b-inst…
Tokens/sec27.021.2
First chunk597 ms468 ms
TTFT8.7 s468 ms
Load time1.8 s9.6 s
Memory usage0.9 GB17.7 GB
Memory %4%14%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
Memory
30/30
Quality
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
qwen3:30b-a3b-instruct-…
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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