Back to leaderboard

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
75 vs 79
Hardware Fit
50 vs 59
Quality Score
86 vs 87

Hardware

qwen2.5:72b qwen3.6-35b-a3b
MachineNVIDIA NVIDIA_DGX_SparkDocker Container
CPUCortex-X925Intel Gen Intel® Core™ i9-11900H
Cores2016
RAM122 GB15 GB
GPUDevice 2e12TigerLake-H GT1 [UHD Graphics]
OSUbuntu 24.04.4 LTSUbuntu 26.04 LTS
Archarm64x64
Power Modeperformanceperformance

Performance

qwen2.5:72b qwen3.6-35b-a3b
Tokens/sec4.49.3
First chunk529 ms21 ms
TTFT529 ms3.6 s
Load time49.7 s32.0 s
Memory usage54.0 GB1.8 GB
Memory %44%12%

HW Fit Score Breakdown

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

qwen3.6-35b-a3b

Speed
17/50
TTFT
12/20
Memory
30/30

Quality

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

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
View qwen2.5:72b details | View qwen3.6-35b-a3b 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