Back to leaderboard

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

qwopus3.6-35b-a3b-coder-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
65 vs 84
Hardware Fit
96 vs 79
Quality Score
51 vs 86

Hardware

qwen3-4b-qwen3.6-p… qwopus3.6-35b-a3b-…
MachineMac StudioASUS
CPUApple M2 MaxAMD Ryzen 7 7800X3D 8-Core Processor
Cores1216
RAM96 GB31 GB
GPUApple M2 MaxNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

qwen3-4b-qwen3.6-p… qwopus3.6-35b-a3b-…
Tokens/sec99.6106.2
First chunk18 ms3 ms
TTFT1.6 s271 ms
Load time4.8 sN/A
Memory usage0.3 GB25.0 GB
Memory %0%82%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
Memory
30/30

qwopus3.6-35b-a3b-coder…

Speed
50/50
TTFT
20/20
Memory
9/30

Quality

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

qwopus3.6-35b-a3b-coder…

Reasoning
16/20
Coding
19/20
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

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