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

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
90 vs 72
Hardware Fit
100 vs 35
Quality Score
86 vs 88

Hardware

qwen3.6-35b-a3b-cl… qwen/qwen3.5-35b-a3b
MachineMacBook ProSystem manufacturer
CPUApple M4 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM128 GB32 GB
GPUApple M4 MaxAMD Radeon RX 9060 XT
OSmacOS 26.5.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.6-35b-a3b-cl… qwen/qwen3.5-35b-a3b
Tokens/sec78.18.3
First chunk7 ms32 ms
TTFT138 ms2.0 s
Load timeN/AN/A
Memory usage23.9 GB28.9 GB
Memory %19%91%

HW Fit Score Breakdown

qwen3.6-35b-a3b-claude-…

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

qwen/qwen3.5-35b-a3b

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

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

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
View qwen3.6-35b-a3b-cl… details | View qwen/qwen3.5-35b-a3b 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