glm-4.7-flash:q4_K_M
OLLAMA GGUFglm4moelite · 29.9B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
81 vs 88
Hardware Fit
89 vs 90
Quality Score
77 vs 87
Hardware
glm-4.7-flash:q4_K_M Qwen3-30B:30b
MachineASUSGMKtec NucBox EVO-T2S
CPUIntel Core™ i5-14600KFIntel Core™ Ultra X7 358H
Cores2016
RAM32 GB64 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERIntel(R) Arc(TM) B390 GPU
OSMicrosoft Windows 11 Famille 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
glm-4.7-flash:q4_K_M Qwen3-30B:30b
Tokens/sec35.131.0
First chunk440 ms549 ms
TTFT440 ms549 ms
Load time11.6 s14.3 s
Memory usage18.4 GB17.7 GB
Memory %58%28%
HW Fit Score Breakdown
glm-4.7-flash:q4_K_M
Speed
49/50
TTFT
20/20
Memory
20/30
Qwen3-30B:30b
Speed
40/50
TTFT
20/20
Memory
30/30
Quality
glm-4.7-flash:q4_K_M
Reasoning
13/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest