Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Xeon® E5-2637 v3

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score
49 vs 66
Hardware Fit
54 vs 40
Quality Score
47 vs 77

Hardware

qwen3.5:35b-a3b-q4… gemma4:31b
MachineDell Inc. Precision Tower 7910ASUSTeK COMPUTER INC. GX10
CPUIntel Xeon® E5-2637 v3Cortex-X925
Cores1620
RAM96 GB122 GB
GPUNVIDIA GeForce RTX 5060 TiDevice 2e12
OSMicrosoft Windows 10 Pro 10.0.19045Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

qwen3.5:35b-a3b-q4… gemma4:31b
Tokens/sec21.610.7
First chunk1505 ms983 ms
TTFT30.0 s20.3 s
Load time53.8 s8.8 s
Memory usage22.7 GB21.4 GB
Memory %24%18%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
24/50
TTFT
0/20
Memory
30/30

gemma4:31b

Speed
10/50
TTFT
0/20
Memory
30/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
5/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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