Back to leaderboard

hf.co/mradermacher/Phr00tyMix-v4-32B-i1-GGUF:Q4_K_M

OLLAMA GGUF

qwen2 · 32.8B · Q4_K_M

Not Rec.

Oct 2, 2026 · Cortex-X925

qwen3.5:9b-mlx

OLLAMA GGUF

nvfp4

Excellent

Aug 25, 2026 · Apple M1 Pro

Global Score
18 vs 84
Hardware Fit
60 vs 94
Quality Score
0 vs 80

Hardware

hf.co/mradermacher… qwen3.5:9b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.5 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced

Performance

hf.co/mradermacher… qwen3.5:9b-mlx
Tokens/sec10.825.0
First chunk103 ms357 ms
TTFT103 ms357 ms
Load time6.3 s3.8 s
Memory usage26.5 GB8.4 GB
Memory %22%52%

HW Fit Score Breakdown

hf.co/mradermacher/Phr0…

Speed
10/50
TTFT
20/20
Memory
30/30

qwen3.5:9b-mlx

Speed
50/50
TTFT
20/20
Memory
24/30

Quality

hf.co/mradermacher/Phr0…

Reasoning
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen3.5:9b-mlx

Reasoning
16/20
Coding
15/20
Instruction
14/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View hf.co/mradermacher… details | View qwen3.5:9b-mlx 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