Back to leaderboard

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
80 vs 67
Hardware Fit
60 vs 67
Quality Score
88 vs 67

Hardware

qwen3-coder:30b codestral:22b
MachineASUSNVIDIA NVIDIA_DGX_Spark
CPUIntel Gen Intel® Core™ i7-12700KCortex-X925
Cores2020
RAM96 GB122 GB
GPUParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060Device 2e12
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

qwen3-coder:30b codestral:22b
Tokens/sec14.717.2
First chunk796 ms129 ms
TTFT796 ms129 ms
Load time0.2 s11.6 s
Memory usage17.9 GB18.9 GB
Memory %19%16%

HW Fit Score Breakdown

qwen3-coder:30b

Speed
14/50
TTFT
19/20
Memory
27/30

codestral:22b

Speed
17/50
TTFT
20/20
Memory
30/30

Quality

qwen3-coder:30b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

codestral:22b

Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-coder:30b details | View codestral:22b 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