qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
qwen3-4b-qwen3.6-plus-reasoning-distilled
LM-STUDIO GGUFqwen3 · 4B · Q4_1
Apr 21, 2026 · Apple M2 Max
Global Score
79 vs 65
Hardware Fit
59 vs 96
Quality Score
87 vs 51
Hardware
qwen3.6-35b-a3b qwen3-4b-qwen3.6-p…
MachineDocker ContainerMac Studio
CPUIntel Gen Intel® Core™ i9-11900HApple M2 Max
Cores1612
RAM15 GB96 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M2 Max
OSUbuntu 26.04 LTSmacOS 26.1
Archx64arm64
Power Modeperformancebalanced
Performance
qwen3.6-35b-a3b qwen3-4b-qwen3.6-p…
Tokens/sec9.399.6
First chunk21 ms18 ms
TTFT3.6 s1.6 s
Load time32.0 s4.8 s
Memory usage1.8 GB0.3 GB
Memory %12%0%
HW Fit Score Breakdown
qwen3.6-35b-a3b
Speed
17/50
TTFT
12/20
Memory
30/30
qwen3-4b-qwen3.6-plus-r…
Speed
50/50
TTFT
16/20
Memory
30/30
Quality
qwen3.6-35b-a3b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-4b-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
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest