qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_0
Feb 28, 2026 · Apple M4 Pro
Global Score
79 vs 72
Hardware Fit
59 vs 100
Quality Score
87 vs 60
Hardware
qwen3.6-35b-a3b mistral:latest
MachineDocker ContainerMac Mini
CPUIntel Gen Intel® Core™ i9-11900HApple M4 Pro
Cores1614
RAM15 GB64 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4 Pro
OSUbuntu 26.04 LTSmacOS 15.7.4
Archx64arm64
Power Modeperformanceunknown
Performance
qwen3.6-35b-a3b mistral:latest
Tokens/sec9.354.3
First chunk21 msN/A
TTFT3.6 s124 ms
Load time32.0 s0.0 s
Memory usage1.8 GB9.9 GB
Memory %12%15%
HW Fit Score Breakdown
qwen3.6-35b-a3b
Speed
17/50
TTFT
12/20
Memory
30/30
mistral:latest
Speed
40/50
TTFT
30/20
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
mistral:latest
Reasoning
8/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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