Back to leaderboard

qwen3.5-9b@q5_k_xl

LM-STUDIO GGUF

qwen35 · 9B · Q5_K_XL

Good

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

deepseek-r1:latest

OLLAMA GGUF

qwen2 · 7.6B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score
73 vs 22
Hardware Fit
47 vs 69
Quality Score
84 vs 2

Hardware

qwen3.5-9b@q5_k_xl deepseek-r1:latest
MachineDocker ContainerNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Gen Intel® Core™ i9-11900HCortex-A78AE
Cores166
RAM15 GB7 GB
GPUTigerLake-H GT1 [UHD Graphics]Integrated / Unknown
OSUbuntu 26.04 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5-9b@q5_k_xl deepseek-r1:latest
Tokens/sec5.69.6
First chunk19 ms1300 ms
TTFT5.6 s1.3 s
Load time12.5 s19.9 s
Memory usage0.0 GB4.8 GB
Memory %0%65%

HW Fit Score Breakdown

qwen3.5-9b@q5_k_xl

Speed
10/50
TTFT
7/20
Memory
30/30

deepseek-r1:latest

Speed
31/50
TTFT
20/20
Memory
18/30

Quality

qwen3.5-9b@q5_k_xl

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

deepseek-r1:latest

Reasoning
0/20
Coding
1/20
Instruction
0/20
Structured
0/15
Math
1/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3.5-9b@q5_k_xl details | View deepseek-r1:latest 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