Back to leaderboard

qwen3.5:35b-a3b-q4_K_M

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

google/gemma-4-e4b-it-qat

LM-STUDIO GGUF

gemma4 · Q4_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
35 vs 78
Hardware Fit
45 vs 68
Quality Score
30 vs 82

Hardware

qwen3.5:35b-a3b-q4… google/gemma-4-e4b…
MachineMicro-Star International Co., Ltd. MS-7D98Docker Container
CPUIntel Core™ i9-14900KIntel Gen Intel® Core™ i9-11900H
Cores3216
RAM128 GB15 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000TigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance

Performance

qwen3.5:35b-a3b-q4… google/gemma-4-e4b…
Tokens/sec16.711.4
First chunk781 ms26 ms
TTFT30.0 s2.2 s
Load time19.9 s5.9 s
Memory usage21.8 GB0.0 GB
Memory %17%0%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

Speed
15/50
TTFT
0/20
Memory
30/30

google/gemma-4-e4b-it-qat

Speed
21/50
TTFT
17/20
Memory
30/30

Quality

qwen3.5:35b-a3b-q4_K_M

Reasoning
8/20
Coding
0/20
Instruction
4/20
Structured
3/15
Math
6/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

google/gemma-4-e4b-it-qat

Reasoning
14/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate 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