hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_M
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 21, 2026 · AMD RYZEN AI MAX+ 395
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor
Global Score
68 vs 78
Hardware Fit
69 vs 86
Quality Score
67 vs 74
Hardware
hf.co/unsloth/Qwen… qwen3:8b
MachineAZW GTR Pro—
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 9 3900X 12-Core Processor
Cores3224
RAM125 GB64 GB
GPURadeon 8060SNVIDIA GeForce RTX 4060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
hf.co/unsloth/Qwen… qwen3:8b
Tokens/sec21.148.5
First chunk571 ms202 ms
TTFT571 ms4.3 s
Load time4.9 s4.2 s
Memory usage22.7 GB5.5 GB
Memory %18%9%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
20/50
TTFT
19/20
Memory
30/30
qwen3:8b
Speed
50/50
TTFT
6/20
Memory
30/30
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
qwen3:8b
Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest