qwen3.6-35b-a3b-mtp
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
77 vs 75
Hardware Fit
55 vs 50
Quality Score
86 vs 86
Hardware
qwen3.6-35b-a3b-mtp qwen2.5:72b
MachineDocker ContainerNVIDIA NVIDIA_DGX_Spark
CPUIntel Gen Intel® Core™ i9-11900HCortex-X925
Cores1620
RAM15 GB122 GB
GPUTigerLake-H GT1 [UHD Graphics]Device 2e12
OSUbuntu 26.04 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance
Performance
qwen3.6-35b-a3b-mtp qwen2.5:72b
Tokens/sec9.24.4
First chunk38 ms529 ms
TTFT4.7 s529 ms
Load time46.7 s49.7 s
Memory usage0.0 GB54.0 GB
Memory %0%44%
HW Fit Score Breakdown
qwen3.6-35b-a3b-mtp
Speed
16/50
TTFT
9/20
Memory
30/30
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
Quality
qwen3.6-35b-a3b-mtp
Reasoning
16/20
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
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest