devstral-small-2-24b-instruct-2512
LM-STUDIO GGUFmistral3 · 24B · IQ4_XS
Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 6bit
Jul 17, 2026 · Apple M5 Max
Global Score
81 vs 87
Hardware Fit
80 vs 90
Quality Score
81 vs 86
Hardware
devstral-small-2-2… qwen/qwen3.6-35b-a3b
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M5 Max
Cores1618
RAM31 GB64 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M5 Max
OSUbuntu 26.04.1 LTSmacOS 27.0
Archx64arm64
Power Modeperformancebalanced
Performance
devstral-small-2-2… qwen/qwen3.6-35b-a3b
Tokens/sec21.586.5
First chunk12 ms9 ms
TTFT212 ms175 ms
Load timeN/AN/A
Memory usage15.9 GB37.9 GB
Memory %51%59%
HW Fit Score Breakdown
devstral-small-2-24b-in…
Speed
35/50
TTFT
20/20
Memory
25/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
20/30
Quality
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
qwen/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
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