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:bf16

OLLAMA GGUF

deepseek2 · 29.9B · F16

Good

Jun 26, 2026 · Cortex-X925

Global Score
78 vs 76
Hardware Fit
59 vs 73
Quality Score
86 vs 77

Hardware

qwen2.5-coder:32b glm-4.7-flash:bf16
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA_DGX_Spark
CPUCortex-X925Cortex-X925
Cores2020
RAM122 GB122 GB
GPUDevice 2e12Device 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archarm64arm64
Power Modeperformanceperformance

Performance

qwen2.5-coder:32b glm-4.7-flash:bf16
Tokens/sec9.525.8
First chunk394 ms605 ms
TTFT395 ms605 ms
Load time72.1 s44.2 s
Memory usage26.5 GB57.0 GB
Memory %22%47%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

glm-4.7-flash:bf16

Speed
27/50
TTFT
20/20
Memory
26/30

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:bf16

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 qwen2.5-coder:32b details | View glm-4.7-flash:bf16 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