Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 26, 2026 · Apple M1 Pro

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
68 vs 67
Hardware Fit
86 vs 67
Quality Score
60 vs 67

Hardware

qwen3.5:4b codestral:22b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5:4b codestral:22b
Tokens/sec36.517.2
First chunk207 ms129 ms
TTFT6.6 s129 ms
Load time3.2 s11.6 s
Memory usage5.3 GB18.9 GB
Memory %33%16%

HW Fit Score Breakdown

qwen3.5:4b

Speed
50/50
TTFT
7/20
Memory
29/30

codestral:22b

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

Quality

qwen3.5:4b

Reasoning
16/20
Coding
1/20
Instruction
12/20
Structured
9/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Strong 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 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