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-claude-4.7-opus-reasoning-distilled-apex-mtp

LM-STUDIO GGUF

qwen35moe · 35B

Excellent

Jun 19, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
75 vs 89
Hardware Fit
50 vs 90
Quality Score
86 vs 88

Hardware

qwen2.5:72b qwen3.6-35b-a3b-cl…
MachineNVIDIA NVIDIA_DGX_SparkGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUCortex-X925AMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM122 GB47 GB
GPUDevice 2e12AD106 [GeForce RTX 4060 Ti]
OSUbuntu 24.04.4 LTScachyos rolling
Archarm64x64
Power Modeperformancelow-power

Performance

qwen2.5:72b qwen3.6-35b-a3b-cl…
Tokens/sec4.442.2
First chunk529 ms40 ms
TTFT529 ms2.7 s
Load time49.7 sN/A
Memory usage54.0 GB21.9 GB
Memory %44%47%

HW Fit Score Breakdown

qwen2.5:72b

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

qwen3.6-35b-a3b-claude-…

Speed
50/50
TTFT
14/20
Memory
26/30

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-claude-…

Reasoning
19/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen2.5:72b details | View qwen3.6-35b-a3b-cl… 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