mistralai/devstral-small-2-2512
LM-STUDIO MLXmistral3 · 24B · 4bit
Oct 20, 2026 · Apple M1 Pro
qwen/qwen3-vl-30b
LM-STUDIO GGUFqwen3vlmoe · 30B · Q4_K_M
Apr 24, 2026 · AMD Ryzen 5 5500
Global Score
73 vs 92
Hardware Fit
64 vs 95
Quality Score
77 vs 90
Hardware
mistralai/devstral… qwen/qwen3-vl-30b
MachineMacBook ProASUS
CPUApple M1 ProAMD Ryzen 5 5500
Cores1012
RAM32 GB31 GB
GPUApple M1 ProNavi 44 [Radeon RX 9060 XT]
OSmacOS 15.6.1Nobara Linux 43
Archarm64x64
Power Modebalancedperformance
Performance
mistralai/devstral… qwen/qwen3-vl-30b
Tokens/sec11.924.8
First chunk7 ms11 ms
TTFT1.1 s735 ms
Load timeN/A11.7 s
Memory usage19.7 GB0.6 GB
Memory %62%2%
HW Fit Score Breakdown
mistralai/devstral-smal…
Speed
25/50
TTFT
20/20
Memory
19/30
qwen/qwen3-vl-30b
Speed
45/50
TTFT
20/20
Memory
30/30
Quality
mistralai/devstral-smal…
Reasoning
17/20
Coding
16/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen/qwen3-vl-30b
Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
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