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

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

Global Score
49 vs 83
Hardware Fit
54 vs 96
Quality Score
47 vs 78

Hardware

qwen3.5:35b-a3b-q4… google/gemma-4-e4b
MachineDell Inc. Precision Tower 7910ASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PH
CPUIntel Xeon® E5-2637 v3AMD Ryzen 9 8940HX
Cores1632
RAM96 GB15 GB
GPUNVIDIA GeForce RTX 5060 TiNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610M
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Home Single Language 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… google/gemma-4-e4b
Tokens/sec21.635.9
First chunk1505 ms9 ms
TTFT30.0 s182 ms
Load time53.8 sN/A
Memory usage22.7 GB6.5 GB
Memory %24%43%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

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

google/gemma-4-e4b

Speed
49/50
TTFT
20/20
Memory
27/30

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

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:35b-a3b-q4… details | View google/gemma-4-e4b 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