Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
53 vs 67
Hardware Fit
82 vs 67
Quality Score
41 vs 67

Hardware

qwen3.5:4b-mlx codestral:22b
MachineMac miniNVIDIA NVIDIA_DGX_Spark
CPUApple M2Cortex-X925
Cores820
RAM8 GB122 GB
GPUApple M2Device 2e12
OSmacOS 26.5.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5:4b-mlx codestral:22b
Tokens/sec24.717.2
First chunk302 ms129 ms
TTFT7.4 s129 ms
Load time3.2 s11.6 s
Memory usage3.8 GB18.9 GB
Memory %47%16%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

codestral:22b

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak 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 qwen3.5:4b-mlx 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