Back to leaderboard

qwen2.5-coder:32b

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

mistral-small:24b

OLLAMA GGUF

llama · 23.6B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

Global Score
78 vs 75
Hardware Fit
59 vs 64
Quality Score
86 vs 80

Hardware

qwen2.5-coder:32b mistral-small:24b
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 mistral-small:24b
Tokens/sec9.514.3
First chunk394 ms327 ms
TTFT395 ms327 ms
Load time72.1 s12.0 s
Memory usage26.5 GB18.5 GB
Memory %22%15%

HW Fit Score Breakdown

qwen2.5-coder:32b

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

mistral-small:24b

Speed
14/50
TTFT
20/20
Memory
30/30

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

mistral-small:24b

Reasoning
16/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen2.5-coder:32b details | View mistral-small:24b 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