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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
18 vs 80
Hardware Fit
60 vs 83
Quality Score
0 vs 79

Hardware

hf.co/mradermacher… google/gemma-4-e4b
MachineNVIDIA NVIDIA_DGX_SparkGMKtec EVO-X3
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB120 GB
GPUDevice 2e12AMD Radeon(TM) 8060S Graphics
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modeperformancebalanced

Performance

hf.co/mradermacher… google/gemma-4-e4b
Tokens/sec10.846.5
First chunk103 ms14 ms
TTFT103 ms1.9 s
Load time6.3 s7.6 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

google/gemma-4-e4b

Speed
43/50
TTFT
10/20
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

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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