Back to leaderboard

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

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
72 vs 62
Hardware Fit
35 vs 10
Quality Score
88 vs 84

Hardware

qwen/qwen3.5-35b-a3b Qwen3-80B:80B
MachineSystem manufacturerHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUAMD Ryzen 7 5800X 8-Core ProcessorAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1632
RAM32 GB31 GB
GPUAMD Radeon RX 9060 XTAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b Qwen3-80B:80B
Tokens/sec8.34.9
First chunk32 ms8006 ms
TTFT2.0 s8.0 s
Load timeN/A63.7 s
Memory usage28.9 GB47.3 GB
Memory %91%153%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

Qwen3-80B:80B

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

Quality

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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