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

Qwen3.8-27B-UD-Q3_K_XL

OLLAMA GGUF

llama · 27.3B · Q4_K

Excellent

Aug 23, 2026 · Intel Gen Intel® Core™ i5-12600K

Global Score
86 vs 90
Hardware Fit
74 vs 97
Quality Score
91 vs 87

Hardware

glm-4.7-flash:latest Qwen3.8-27B-UD-Q3_…
MachineAZW GTR Pro
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i5-12600K
Cores3216
RAM125 GB31 GB
GPURadeon 8060SAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modeperformancelow-power

Performance

glm-4.7-flash:latest Qwen3.8-27B-UD-Q3_…
Tokens/sec47.839.0
First chunk194 ms305 ms
TTFT30.0 s305 ms
Load time7.4 s0.0 s
Memory usage37.7 GB12.5 GB
Memory %30%41%

HW Fit Score Breakdown

glm-4.7-flash:latest

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

Qwen3.8-27B-UD-Q3_K_XL

Speed
50/50
TTFT
20/20
Memory
27/30

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

Qwen3.8-27B-UD-Q3_K_XL

Reasoning
17/20
Coding
19/20
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

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