devstral:24b
OLLAMA GGUFllama · 23.6B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
Global Score
80 vs 97
Hardware Fit
79 vs 95
Quality Score
80 vs 98
Hardware
devstral:24b qwen3-30b-a3b-thin…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Mac Studio
CPUIntel Core™ i5-14400FApple M2 Max
Cores1612
RAM32 GB96 GB
GPUNVIDIA GeForce RTX 5060 TiApple M2 Max
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
devstral:24b qwen3-30b-a3b-thin…
Tokens/sec20.279.6
First chunk137 ms11 ms
TTFT137 ms1.7 s
Load time9.6 s7.1 s
Memory usage14.2 GB0.0 GB
Memory %45%0%
HW Fit Score Breakdown
devstral:24b
Speed
33/50
TTFT
20/20
Memory
26/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
Quality
devstral:24b
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
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