Back to leaderboard

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 19, 2026 · Apple M4 Max

Global Score
67 vs 89
Hardware Fit
67 vs 96
Quality Score
67 vs 86

Hardware

codestral:22b qwen3-coder:30b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M4 Max
Cores2016
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Max
OSUbuntu 24.04.4 LTSmacOS 26.5.1
Archarm64arm64
Power Modeperformancebalanced

Performance

codestral:22b qwen3-coder:30b
Tokens/sec17.289.9
First chunk129 ms188 ms
TTFT129 ms188 ms
Load time11.6 s4.0 s
Memory usage18.9 GB30.2 GB
Memory %16%47%

HW Fit Score Breakdown

codestral:22b

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

qwen3-coder:30b

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

Quality

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

qwen3-coder:30b

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: Adequate Multilingual: Strong
View codestral:22b details | View qwen3-coder:30b 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