Back to leaderboard

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

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jul 17, 2026 · Apple M5 Max

qwopus3.6-27b-coder-compat-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
90 vs 88
Hardware Fit
98 vs 80
Quality Score
86 vs 91

Hardware

qwen3.6-35b-a3b-cl… qwopus3.6-27b-code…
MachineMacBook ProASUS
CPUApple M5 MaxAMD Ryzen 7 7800X3D 8-Core Processor
Cores1816
RAM64 GB31 GB
GPUApple M5 MaxNVIDIA GeForce RTX 4090, Raphael
OSmacOS 27.0cachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.6-35b-a3b-cl… qwopus3.6-27b-code…
Tokens/sec86.680.8
First chunk13 ms6 ms
TTFT143 ms226 ms
Load timeN/AN/A
Memory usage23.9 GB24.6 GB
Memory %37%81%

HW Fit Score Breakdown

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
20/20
Memory
28/30

qwopus3.6-27b-coder-com…

Speed
50/50
TTFT
20/20
Memory
10/30

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

qwopus3.6-27b-coder-com…

Reasoning
19/20
Coding
18/20
Instruction
17/20
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 qwopus3.6-27b-code… 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