Back to leaderboard

devstral-small-2-24b-instruct-2512

LM-STUDIO GGUF

mistral3 · 24B · IQ4_XS

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
81 vs 72
Hardware Fit
80 vs 35
Quality Score
81 vs 88

Hardware

devstral-small-2-2… qwen/qwen3.5-35b-a3b
MachineSystem manufacturerSystem manufacturer
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM31 GB32 GB
GPUNavi 44 [Radeon RX 9060 XT]AMD Radeon RX 9060 XT
OSUbuntu 26.04.1 LTSMicrosoft Windows 11 Home 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

devstral-small-2-2… qwen/qwen3.5-35b-a3b
Tokens/sec21.58.3
First chunk12 ms32 ms
TTFT212 ms2.0 s
Load timeN/AN/A
Memory usage15.9 GB28.9 GB
Memory %51%91%

HW Fit Score Breakdown

devstral-small-2-24b-in…

Speed
35/50
TTFT
20/20
Memory
25/30

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

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/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest