Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

glm-4.7-flash:latest

OLLAMA GGUF

glm4moelite · 29.9B · Q4_K_M

Not Rec.

Mar 22, 2026 · AMD RYZEN AI MAX+ 395

Global Score
78 vs 86
Hardware Fit
86 vs 74
Quality Score
74 vs 91

Hardware

qwen3:8b glm-4.7-flash:latest
MachineAZW GTR Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorAMD RYZEN AI MAX+ 395
Cores2432
RAM64 GB125 GB
GPUNVIDIA GeForce RTX 4060 TiRadeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3:8b glm-4.7-flash:latest
Tokens/sec48.547.8
First chunk202 ms194 ms
TTFT4.3 s30.0 s
Load time4.2 s7.4 s
Memory usage5.5 GB37.7 GB
Memory %9%30%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
6/20
Memory
30/30

glm-4.7-flash:latest

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

Quality

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

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

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