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

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

Global Score
18 vs 89
Hardware Fit
60 vs 95
Quality Score
0 vs 87

Hardware

hf.co/mradermacher… qwen/qwen3-8b
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.5 LTSmacOS 15.7.4
Archarm64arm64
Power Modeperformancebalanced

Performance

hf.co/mradermacher… qwen/qwen3-8b
Tokens/sec10.833.4
First chunk103 ms257 ms
TTFT103 ms257 ms
Load time6.3 sN/A
Memory usage26.5 GB4.3 GB
Memory %22%7%

HW Fit Score Breakdown

hf.co/mradermacher/Phr0…

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

qwen/qwen3-8b

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

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

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View hf.co/mradermacher… details | View qwen/qwen3-8b 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