Back to leaderboard

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Not Rec.

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
86 vs 75
Hardware Fit
74 vs 50
Quality Score
91 vs 86

Hardware

glm-4.7-flash:latest qwen2.5:72b
MachineAZW GTR ProNVIDIA NVIDIA_DGX_Spark
CPUAMD RYZEN AI MAX+ 395Cortex-X925
Cores3220
RAM125 GB122 GB
GPURadeon 8060SDevice 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modeperformanceperformance

Performance

glm-4.7-flash:latest qwen2.5:72b
Tokens/sec47.84.4
First chunk194 ms529 ms
TTFT30.0 s529 ms
Load time7.4 s49.7 s
Memory usage37.7 GB54.0 GB
Memory %30%44%

HW Fit Score Breakdown

glm-4.7-flash:latest

Speed
44/50
TTFT
0/20
Memory
30/30

qwen2.5:72b

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

Quality

glm-4.7-flash:latest

Reasoning
19/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
15/15
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 glm-4.7-flash:latest 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