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/qwen3.8-27b

LM-STUDIO MLX

qwen3_5 · 27B · 4bit

Excellent

Aug 19, 2026 · Apple M4 Max

Global Score
18 vs 84
Hardware Fit
60 vs 69
Quality Score
0 vs 90

Hardware

hf.co/mradermacher… qwen/qwen3.8-27b
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M4 Max
Cores2016
RAM122 GB128 GB
GPUDevice 2e12Apple M4 Max
OSUbuntu 24.04.5 LTSmacOS 26.5.2
Archarm64arm64
Power Modeperformancebalanced

Performance

hf.co/mradermacher… qwen/qwen3.8-27b
Tokens/sec10.828.9
First chunk103 ms33 ms
TTFT103 ms4.4 s
Load time6.3 s7.9 s
Memory usage26.5 GB0.0 GB
Memory %22%0%

HW Fit Score Breakdown

hf.co/mradermacher/Phr0…

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

qwen/qwen3.8-27b

Speed
33/50
TTFT
6/20
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/qwen3.8-27b

Reasoning
19/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View hf.co/mradermacher… details | View qwen/qwen3.8-27b 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