Back to leaderboard

qwen3.8:latest

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Good

Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor

glm-4.7-flash-reap-39-i1

LM-STUDIO GGUF

deepseek2 · Q5_K_M

Excellent

Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
68 vs 80
Hardware Fit
22 vs 97
Quality Score
88 vs 73

Hardware

qwen3.8:latest glm-4.7-flash-reap…
MachineSystem manufacturerMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 9 5950X 16-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores3216
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 3090NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.8:latest glm-4.7-flash-reap…
Tokens/sec10.0154.8
First chunk1041 ms13 ms
TTFT14.3 s70 ms
Load time22.3 sN/A
Memory usage26.2 GB12.6 GB
Memory %82%41%

HW Fit Score Breakdown

qwen3.8:latest

Speed
12/50
TTFT
1/20
Memory
9/30

glm-4.7-flash-reap-39-i1

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

Quality

qwen3.8:latest

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

glm-4.7-flash-reap-39-i1

Reasoning
13/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Adequate
View qwen3.8:latest details | View glm-4.7-flash-reap… 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