qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
qwen3-coder-next:latest
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
83 vs 82
Hardware Fit
70 vs 71
Quality Score
89 vs 87
Hardware
qwen3:30b-a3b-inst… qwen3-coder-next:l…
MachineMicro-Star International Co., Ltd. MS-7D98AZW GTR Pro
CPUIntel Core™ i9-14900KAMD RYZEN AI MAX+ 395
Cores3232
RAM128 GB125 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000AMD Radeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance
Performance
qwen3:30b-a3b-inst… qwen3-coder-next:l…
Tokens/sec21.034.5
First chunk473 ms262 ms
TTFT473 ms262 ms
Load time8.6 s16.4 s
Memory usage17.7 GB56.8 GB
Memory %14%46%
HW Fit Score Breakdown
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
Memory
30/30
qwen3-coder-next:latest
Speed
34/50
TTFT
20/20
Memory
17/30
Quality
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
qwen3-coder-next:latest
Reasoning
18/20
Coding
18/20
Instruction
13/20
Structured
15/15
Math
13/15
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