Back to leaderboard

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

qwen3.6:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Jun 25, 2026 · Apple M4 Pro

Global Score
67 vs 20
Hardware Fit
67 vs 34
Quality Score
67 vs 14

Hardware

codestral:22b qwen3.6:27b
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4 Pro
Cores2012
RAM122 GB24 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.6.1
Archarm64arm64
Power Modeperformancebalanced

Performance

codestral:22b qwen3.6:27b
Tokens/sec17.210.6
First chunk129 ms1344 ms
TTFT129 ms30.0 s
Load time11.6 s0.2 s
Memory usage18.9 GB18.1 GB
Memory %16%75%

HW Fit Score Breakdown

codestral:22b

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

qwen3.6:27b

Speed
22/50
TTFT
0/20
Memory
12/30

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

qwen3.6:27b

Reasoning
2/20
Coding
1/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
6/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate

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