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

Qwen3-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
35 vs 62
Hardware Fit
45 vs 10
Quality Score
30 vs 84

Hardware

qwen3.5:35b-a3b-q4… Qwen3-80B:80B
MachineMicro-Star International Co., Ltd. MS-7D98HP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Core™ i9-14900KAMD Ryzen 9 9955HX3D 16-Core Processor
Cores3232
RAM128 GB31 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b-q4… Qwen3-80B:80B
Tokens/sec16.74.9
First chunk781 ms8006 ms
TTFT30.0 s8.0 s
Load time19.9 s63.7 s
Memory usage21.8 GB47.3 GB
Memory %17%153%

HW Fit Score Breakdown

qwen3.5:35b-a3b-q4_K_M

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

Qwen3-80B:80B

Speed
6/50
TTFT
4/20
Memory
0/30

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

Qwen3-80B:80B

Reasoning
17/20
Coding
19/20
Instruction
13/20
Structured
13/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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