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-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
80 vs 83
Hardware Fit
60 vs 96
Quality Score
88 vs 78

Hardware

qwen/qwen3.6-35b-a3b qwen3-vl:4b-instruct
MachineSystem manufacturerMac Studio
CPUAMD Ryzen 7 5800X 8-Core ProcessorApple M2 Max
Cores1612
RAM31 GB96 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M2 Max
OSUbuntu 26.04.1 LTSmacOS 26.1
Archx64arm64
Power Modeperformancebalanced

Performance

qwen/qwen3.6-35b-a3b qwen3-vl:4b-instruct
Tokens/sec15.090.6
First chunk49 ms159 ms
TTFT759 ms159 ms
Load timeN/A5.8 s
Memory usage22.2 GB42.5 GB
Memory %71%44%

HW Fit Score Breakdown

qwen/qwen3.6-35b-a3b

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

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

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-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen/qwen3.6-35b-a3b details | View qwen3-vl:4b-instruct 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