Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

qwen2.5-coder:7b

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Good

Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K

Global Score
84 vs 68
Hardware Fit
66 vs 59
Quality Score
92 vs 72

Hardware

qwen3.8:27b qwen2.5-coder:7b
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925Intel Gen Intel® Core™ i7-13700K
Cores2024
RAM122 GB64 GB
GPUDevice 2e12NVIDIA GeForce RTX 3070
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformanceunknown

Performance

qwen3.8:27b qwen2.5-coder:7b
Tokens/sec29.434.4
First chunk306 ms1991 ms
TTFT4.8 s2.0 s
Load time5.3 s40.6 s
Memory usage16.2 GB5.0 GB
Memory %13%8%

HW Fit Score Breakdown

qwen3.8:27b

Speed
31/50
TTFT
5/20
Memory
30/30

qwen2.5-coder:7b

Speed
38/50
TTFT
12/20
Memory
9/30

Quality

qwen3.8:27b

Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen2.5-coder:7b

Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.8:27b details | View qwen2.5-coder:7b 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