Back to leaderboard

qwen3.8-27b-uncensored-ymq-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 12, 2026 · AMD Ryzen 5 5600X 6-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
84 vs 70
Hardware Fit
81 vs 39
Quality Score
85 vs 83

Hardware

qwen3.8-27b-uncens… qwen3-next-80b-t48…
MachineGigabyte Technology Co., Ltd. X570 AORUS PRODell Inc. PowerEdge R820
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Xeon® E5-4620 0
Cores1264
RAM32 GB256 GB
GPUNVIDIA GeForce RTX 5070 TiMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows Server 2022 Datacenter 10.0.20348
Archx64x64
Power Modebalancedbalanced

Performance

qwen3.8-27b-uncens… qwen3-next-80b-t48…
Tokens/sec18.33.0
First chunk9 ms3265 ms
TTFT522 ms3.3 s
Load time7.7 s82.1 s
Memory usage14.9 GB46.9 GB
Memory %47%18%

HW Fit Score Breakdown

qwen3.8-27b-uncensored-…

Speed
35/50
TTFT
20/20
Memory
26/30

qwen3-next-80b-t48:latest

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

Quality

qwen3.8-27b-uncensored-…

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