Back to leaderboard

qwen3:32b

OLLAMA GGUF

qwen3 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

glm-4.7-flash:q4_K_M

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Excellent

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
79 vs 81
Hardware Fit
59 vs 89
Quality Score
88 vs 77

Hardware

qwen3:32b glm-4.7-flash:q4_K_M
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925Intel Core™ i5-14600KF
Cores2020
RAM122 GB32 GB
GPUDevice 2e12NVIDIA GeForce RTX 4070 Ti SUPER
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

qwen3:32b glm-4.7-flash:q4_K_M
Tokens/sec9.735.1
First chunk324 ms440 ms
TTFT324 ms440 ms
Load time24.5 s11.6 s
Memory usage26.8 GB18.4 GB
Memory %22%58%

HW Fit Score Breakdown

qwen3:32b

Speed
9/50
TTFT
20/20
Memory
30/30

glm-4.7-flash:q4_K_M

Speed
49/50
TTFT
20/20
Memory
20/30

Quality

qwen3:32b

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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
View qwen3:32b details | View glm-4.7-flash:q4_K_M 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