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

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 24, 2026 · Intel Core™ Ultra X7 358H

Global Score
86 vs 88
Hardware Fit
74 vs 90
Quality Score
91 vs 87

Hardware

glm-4.7-flash:latest Qwen3-30B:30b
MachineAZW GTR ProGMKtec NucBox EVO-T2S
CPUAMD RYZEN AI MAX+ 395Intel Core™ Ultra X7 358H
Cores3216
RAM125 GB64 GB
GPURadeon 8060SIntel(R) Arc(TM) B390 GPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

glm-4.7-flash:latest Qwen3-30B:30b
Tokens/sec47.831.3
First chunk194 ms560 ms
TTFT30.0 s560 ms
Load time7.4 s15.4 s
Memory usage37.7 GB17.7 GB
Memory %30%28%

HW Fit Score Breakdown

glm-4.7-flash:latest

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

Qwen3-30B:30b

Speed
40/50
TTFT
20/20
Memory
30/30

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

Qwen3-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View glm-4.7-flash:latest details | View Qwen3-30B:30b 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