Back to leaderboard

qwen3.5-35b-a3b-mtp

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

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

llama3.1:8b

OLLAMA GGUF

llama · 8.0B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
77 vs 81
Hardware Fit
51 vs 100
Quality Score
88 vs 73

Hardware

qwen3.5-35b-a3b-mtp llama3.1:8b
MachineDocker ContainerGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUIntel Gen Intel® Core™ i9-11900HIntel Core™ i5-14400F
Cores1616
RAM15 GB32 GB
GPUTigerLake-H GT1 [UHD Graphics]NVIDIA GeForce RTX 5060 Ti
OSUbuntu 26.04 LTSMicrosoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modeperformancebalanced

Performance

qwen3.5-35b-a3b-mtp llama3.1:8b
Tokens/sec7.870.2
First chunk30 ms58 ms
TTFT5.6 s58 ms
Load time32.5 s4.1 s
Memory usage0.0 GB4.9 GB
Memory %0%15%

HW Fit Score Breakdown

qwen3.5-35b-a3b-mtp

Speed
14/50
TTFT
7/20
Memory
30/30

llama3.1:8b

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

Quality

qwen3.5-35b-a3b-mtp

Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

llama3.1:8b

Reasoning
12/20
Coding
18/20
Instruction
15/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5-35b-a3b-mtp details | View llama3.1:8b 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