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-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
72 vs 70
Hardware Fit
35 vs 39
Quality Score
88 vs 83

Hardware

qwen/qwen3.5-35b-a3b qwen3-next-80b-t48…
MachineSystem manufacturerDell Inc. PowerEdge R820
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Xeon® E5-4620 0
Cores1664
RAM32 GB256 GB
GPUAMD Radeon RX 9060 XTMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Home 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

qwen/qwen3.5-35b-a3b qwen3-next-80b-t48…
Tokens/sec8.33.0
First chunk32 ms3265 ms
TTFT2.0 s3.3 s
Load timeN/A82.1 s
Memory usage28.9 GB46.9 GB
Memory %91%18%

HW Fit Score Breakdown

qwen/qwen3.5-35b-a3b

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

qwen3-next-80b-t48:latest

Speed
3/50
TTFT
6/20
Memory
30/30

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-next-80b-t48:latest

Reasoning
18/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak 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