Back to leaderboard

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
72 vs 75
Hardware Fit
35 vs 50
Quality Score
88 vs 86

Hardware

qwen/qwen3.5-35b-a3b qwen2.5:72b
MachineSystem manufacturerNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 7 5800X 8-Core ProcessorCortex-X925
Cores1620
RAM32 GB122 GB
GPUAMD Radeon RX 9060 XTDevice 2e12
OSMicrosoft Windows 11 Home 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

qwen/qwen3.5-35b-a3b qwen2.5:72b
Tokens/sec8.34.4
First chunk32 ms529 ms
TTFT2.0 s529 ms
Load timeN/A49.7 s
Memory usage28.9 GB54.0 GB
Memory %91%44%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

qwen2.5:72b

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

Quality

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
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
View qwen/qwen3.5-35b-a3b details | View qwen2.5:72b 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