Back to leaderboard

qwen/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

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

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
80 vs 68
Hardware Fit
60 vs 91
Quality Score
88 vs 58

Hardware

qwen/qwen3.6-35b-a3b qwen3.5:4b-mlx
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M1 Pro
Cores1610
RAM31 GB16 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced

Performance

qwen/qwen3.6-35b-a3b qwen3.5:4b-mlx
Tokens/sec15.042.2
First chunk49 ms201 ms
TTFT759 ms4.4 s
Load timeN/A0.0 s
Memory usage22.2 GB3.8 GB
Memory %71%24%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

Speed
25/50
TTFT
20/20
Memory
15/30

qwen3.5:4b-mlx

Speed
50/50
TTFT
11/20
Memory
30/30

Quality

qwen/qwen3.6-35b-a3b

Reasoning
16/20
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

qwen3.5:4b-mlx

Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View qwen3.5:4b-mlx 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