Back to leaderboard

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_S

Not Rec.

Apr 20, 2026 · Apple M2 Max

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

LM-STUDIO GGUF

mistral3 · 24B · IQ4_XS

Excellent

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

Global Score
82 vs 81
Hardware Fit
80 vs 80
Quality Score
83 vs 81

Hardware

qwen3.6-35b-a3b devstral-small-2-2…
MachineMac StudioSystem manufacturer
CPUApple M2 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1216
RAM96 GB31 GB
GPUApple M2 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.6-35b-a3b devstral-small-2-2…
Tokens/sec55.221.5
First chunk4 ms12 ms
TTFT30.0 s212 ms
Load timeN/AN/A
Memory usage30.3 GB15.9 GB
Memory %32%51%

HW Fit Score Breakdown

qwen3.6-35b-a3b

Speed
50/50
TTFT
0/20
Memory
30/30

devstral-small-2-24b-in…

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

Quality

qwen3.6-35b-a3b

Reasoning
18/20
Coding
10/20
Instruction
18/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong 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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest