Back to leaderboard

hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_M

OLLAMA GGUF

qwen35 · 27.3B · unknown

Good

Aug 21, 2026 · AMD RYZEN AI MAX+ 395

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
68 vs 74
Hardware Fit
69 vs 99
Quality Score
67 vs 63

Hardware

hf.co/unsloth/Qwen… llama3.2:3b
MachineAZW GTR ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD RYZEN AI MAX+ 395Cortex-A78AE
Cores326
RAM125 GB7 GB
GPURadeon 8060SIntegrated / Unknown
OSUbuntu 24.04.4 LTSUbuntu 22.04.5 LTS
Archx64arm64
Power Modelow-powerbalanced

Performance

hf.co/unsloth/Qwen… llama3.2:3b
Tokens/sec21.121.1
First chunk571 ms1032 ms
TTFT571 ms1.0 s
Load time4.9 s8.4 s
Memory usage22.7 GB2.4 GB
Memory %18%32%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed
20/50
TTFT
19/20
Memory
30/30

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning
12/20
Coding
10/20
Instruction
10/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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