Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

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
78 vs 80
Hardware Fit
59 vs 97
Quality Score
86 vs 73

Hardware

qwen2.5-coder:32b glm-4.7-flash-reap…
MachineNVIDIA NVIDIA_DGX_SparkMicro-Star International Co., Ltd. MS-7E51
CPUCortex-X925AMD Ryzen 7 9700X 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced

Performance

qwen2.5-coder:32b glm-4.7-flash-reap…
Tokens/sec9.5154.8
First chunk394 ms13 ms
TTFT395 ms70 ms
Load time72.1 sN/A
Memory usage26.5 GB12.6 GB
Memory %22%41%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

glm-4.7-flash-reap-39-i1

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

Quality

qwen2.5-coder:32b

Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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 qwen2.5-coder:32b 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