Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 5, 2026 · Apple M1 Max

codestral:22b

OLLAMA GGUF

llama · 22.2B · Q4_0

Good

Jun 26, 2026 · Cortex-X925

Global Score
85 vs 67
Hardware Fit
95 vs 67
Quality Score
80 vs 67

Hardware

qwen3.5:9b codestral:22b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 MaxCortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M1 MaxDevice 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

qwen3.5:9b codestral:22b
Tokens/sec23.117.2
First chunk358 ms129 ms
TTFT358 ms129 ms
Load time3.6 s11.6 s
Memory usage9.1 GB18.9 GB
Memory %28%16%

HW Fit Score Breakdown

qwen3.5:9b

Speed
45/50
TTFT
20/20
Memory
30/30

codestral:22b

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

Quality

qwen3.5:9b

Reasoning
14/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong 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 qwen3.5:9b 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