Back to leaderboard

Qwen3.6-35B-A3B-Q4_K_M:latest

OLLAMA GGUF

qwen35moe · 34.7B · Q4_K_M

Excellent

Aug 18, 2026 · AMD Ryzen 7 9700X 8-Core Processor

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
86 vs 84
Hardware Fit
87 vs 100
Quality Score
86 vs 77

Hardware

Qwen3.6-35B-A3B-Q4… laguna-xs-2.1
MachineMicro-Star International Co., Ltd. MS-7E51AZW GTR Pro
CPUAMD Ryzen 7 9700X 8-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1632
RAM31 GB125 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsRadeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

Qwen3.6-35B-A3B-Q4… laguna-xs-2.1
Tokens/sec92.965.9
First chunk362 ms281 ms
TTFT362 ms281 ms
Load time12.3 s9.9 s
Memory usage20.7 GB30.1 GB
Memory %67%24%

HW Fit Score Breakdown

Qwen3.6-35B-A3B-Q4_K_M:…

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

laguna-xs-2.1

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

Quality

Qwen3.6-35B-A3B-Q4_K_M:…

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

laguna-xs-2.1

Reasoning
8/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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