Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Good

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

qwen3.8:27b-bf16

OLLAMA GGUF

qwen35 · 27.3B · BF16

Excellent

Aug 22, 2026 · AMD EPYC 7713 64-Core Processor

Global Score
78 vs 85
Hardware Fit
47 vs 77
Quality Score
92 vs 88

Hardware

gemma4:31b qwen3.8:27b-bf16
MachineAZW GTR ProDell Inc. PowerEdge XE8545
CPUAMD RYZEN AI MAX+ 395AMD EPYC 7713 64-Core Processor
Cores32128
RAM125 GB1007 GB
GPURadeon 8060SGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]
OSUbuntu 24.04.4 LTSRocky Linux 8.10
Archx64x64
Power Modeperformanceunknown

Performance

gemma4:31b qwen3.8:27b-bf16
Tokens/sec9.827.2
First chunk873 ms237 ms
TTFT873 ms237 ms
Load time7.0 s43.8 s
Memory usage68.3 GB68.8 GB
Memory %55%7%

HW Fit Score Breakdown

gemma4:31b

Speed
8/50
TTFT
16/20
Memory
23/30

qwen3.8:27b-bf16

Speed
27/50
TTFT
20/20
Memory
30/30

Quality

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.8:27b-bf16

Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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