Back to leaderboard

qwen3.6-35b-a3b-claude-4.7-opus-reasoning-distilled-apex

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Aug 19, 2026 · Apple M4 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
90 vs 81
Hardware Fit
100 vs 80
Quality Score
86 vs 81

Hardware

qwen3.6-35b-a3b-cl… devstral-small-2-2…
MachineMacBook ProSystem manufacturer
CPUApple M4 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM128 GB31 GB
GPUApple M4 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.5.2Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.6-35b-a3b-cl… devstral-small-2-2…
Tokens/sec78.121.5
First chunk7 ms12 ms
TTFT138 ms212 ms
Load timeN/AN/A
Memory usage23.9 GB15.9 GB
Memory %19%51%

HW Fit Score Breakdown

qwen3.6-35b-a3b-claude-…

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

devstral-small-2-24b-in…

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

Quality

qwen3.6-35b-a3b-claude-…

Reasoning
18/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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
View qwen3.6-35b-a3b-cl… details | View devstral-small-2-2… details

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