qwen3-coder:30b-a3b-q8_0
OLLAMA GGUFqwen3moe · 30.5B · Q8_0
Jun 18, 2026 · Intel Core™ Ultra 9 285HX
devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
Global Score
90 vs 81
Hardware Fit
89 vs 80
Quality Score
90 vs 81
Hardware
qwen3-coder:30b-a3… devstral-small-2-2…
MachineMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJGSystem manufacturer
CPUIntel Core™ Ultra 9 285HXAMD Ryzen 7 5800X 8-Core Processor
Cores2416
RAM63 GB31 GB
GPUIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPUNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Home Single Language 10.0.26200Ubuntu 26.04.1 LTS
Archx64x64
Power Modebalancedperformance
Performance
qwen3-coder:30b-a3… devstral-small-2-2…
Tokens/sec43.121.5
First chunk957 ms12 ms
TTFT957 ms212 ms
Load time52.0 sN/A
Memory usage33.6 GB15.9 GB
Memory %53%51%
HW Fit Score Breakdown
qwen3-coder:30b-a3b-q8_0
Speed
46/50
TTFT
19/20
Memory
24/30
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
Quality
qwen3-coder:30b-a3b-q8_0
Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
devstral-small-2-24b-in…
Reasoning
16/20
Coding
17/20
Instruction
17/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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