Back to leaderboard

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

LM-STUDIO GGUF

qwen35 · 27B

Good

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

qwen2.5-coder:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
78 vs 68
Hardware Fit
56 vs 100
Quality Score
87 vs 54

Hardware

qwen3.8-27b-uncens… qwen2.5-coder:1.5b
MachineSystem manufacturerLENOVO 20U30029MB
CPUAMD Ryzen 7 5800X 8-Core ProcessorIntel Core™ i5-10210U
Cores168
RAM31 GB15 GB
GPUNavi 44 [Radeon RX 9060 XT]CometLake-U GT2 [UHD Graphics]
OSUbuntu 26.04.1 LTSPop 24.04 LTS
Archx64x64
Power Modeperformancelow-power

Performance

qwen3.8-27b-uncens… qwen2.5-coder:1.5b
Tokens/sec7.021.8
First chunk19 ms499 ms
TTFT1.2 s499 ms
Load timeN/A4.4 s
Memory usage15.6 GB1.5 GB
Memory %50%10%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

Speed
11/50
TTFT
20/20
Memory
25/30

qwen2.5-coder:1.5b

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

Quality

qwen3.8-27b-uncensored-…

Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen2.5-coder:1.5b

Reasoning
8/20
Coding
11/20
Instruction
13/20
Structured
11/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
View qwen3.8-27b-uncens… details | View qwen2.5-coder:1.5b 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