Back to leaderboard

qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Excellent

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

spark-x2.5-4b

LM-STUDIO GGUF

spark2_5 · 4B · Q4_K_M

Good

Sep 30, 2026 · AMD Ryzen 7 4800H

Global Score
80 vs 77
Hardware Fit
62 vs 90
Quality Score
88 vs 71

Hardware

qwen3.5-35b-a3b spark-x2.5-4b
MachineDocker ContainerASUSTeK COMPUTER INC. ROG Strix G513IM_G513IM
CPUIntel Gen Intel® Core™ i9-11900HAMD Ryzen 7 4800H
Cores1616
RAM15 GB15 GB
GPUTigerLake-H GT1 [UHD Graphics]AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 3060 Laptop GPU
OSUbuntu 26.04 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5-35b-a3b spark-x2.5-4b
Tokens/sec10.648.9
First chunk52 ms20 ms
TTFT3.2 s168 ms
Load time7.6 sN/A
Memory usage1.1 GB9.4 GB
Memory %7%61%

HW Fit Score Breakdown

qwen3.5-35b-a3b

Speed
19/50
TTFT
13/20
Memory
30/30

spark-x2.5-4b

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

Quality

qwen3.5-35b-a3b

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

spark-x2.5-4b

Reasoning
13/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5-35b-a3b details | View spark-x2.5-4b 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