Back to leaderboard

Qwen3.8-27B-UD-Q3_K_XL

OLLAMA GGUF

llama · 27.3B · Q4_K

Excellent

Aug 23, 2026 · Intel Gen Intel® Core™ i5-12600K

deepseek-coder-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Excellent

Jun 26, 2026 · Cortex-X925

Global Score
90 vs 82
Hardware Fit
97 vs 100
Quality Score
87 vs 74

Hardware

Qwen3.8-27B-UD-Q3_… deepseek-coder-v2:…
MachineNVIDIA NVIDIA_DGX_Spark
CPUIntel Gen Intel® Core™ i5-12600KCortex-X925
Cores1620
RAM31 GB122 GB
GPUAlderLake-S GT1, AD106 [GeForce RTX 4060 Ti 16GB]Device 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance

Performance

Qwen3.8-27B-UD-Q3_… deepseek-coder-v2:…
Tokens/sec39.0117.2
First chunk305 ms275 ms
TTFT305 ms275 ms
Load time0.0 s8.9 s
Memory usage12.5 GB17.9 GB
Memory %41%15%

HW Fit Score Breakdown

Qwen3.8-27B-UD-Q3_K_XL

Speed
50/50
TTFT
20/20
Memory
27/30

deepseek-coder-v2:16b

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

Quality

Qwen3.8-27B-UD-Q3_K_XL

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: Strong Multilingual: Strong

deepseek-coder-v2:16b

Reasoning
8/20
Coding
19/20
Instruction
13/20
Structured
12/15
Math
14/15
Multilingual
8/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate 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