Back to leaderboard

qwen3.6:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Not Rec.

Jun 25, 2026 · Apple M4 Pro

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

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

Hardware

qwen3.6:27b codestral:22b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M4 ProCortex-X925
Cores1220
RAM24 GB122 GB
GPUApple M4 ProDevice 2e12
OSmacOS 15.6.1Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.6:27b codestral:22b
Tokens/sec10.617.2
First chunk1344 ms129 ms
TTFT30.0 s129 ms
Load time0.2 s11.6 s
Memory usage18.1 GB18.9 GB
Memory %75%16%

HW Fit Score Breakdown

qwen3.6:27b

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

codestral:22b

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

Quality

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

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

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