Back to leaderboard

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

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

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
79 vs 81
Hardware Fit
59 vs 64
Quality Score
87 vs 88

Hardware

qwen3.6-35b-a3b qwen3.8-27b-uncens…
MachineDocker ContainerSystem manufacturer
CPUIntel Gen Intel® Core™ i9-11900HAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM15 GB31 GB
GPUTigerLake-H GT1 [UHD Graphics]Navi 44 [Radeon RX 9060 XT]
OSUbuntu 26.04 LTSUbuntu 26.04.1 LTS
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.6-35b-a3b qwen3.8-27b-uncens…
Tokens/sec9.311.7
First chunk21 ms50 ms
TTFT3.6 s1.1 s
Load time32.0 sN/A
Memory usage1.8 GB15.8 GB
Memory %12%51%

HW Fit Score Breakdown

qwen3.6-35b-a3b

Speed
17/50
TTFT
12/20
Memory
30/30

qwen3.8-27b-uncensored-…

Speed
19/50
TTFT
20/20
Memory
25/30

Quality

qwen3.6-35b-a3b

Reasoning
17/20
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

qwen3.8-27b-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.6-35b-a3b details | View qwen3.8-27b-uncens… 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