hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ1_M
OLLAMA GGUFqwen35 · 27.3B · unknown
Aug 21, 2026 · AMD RYZEN AI MAX+ 395
deepseek-coder-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
68 vs 82
Hardware Fit
69 vs 100
Quality Score
67 vs 74
Hardware
hf.co/unsloth/Qwen… deepseek-coder-v2:…
MachineAZW GTR ProNVIDIA NVIDIA_DGX_Spark
CPUAMD RYZEN AI MAX+ 395Cortex-X925
Cores3220
RAM125 GB122 GB
GPURadeon 8060SDevice 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64arm64
Power Modelow-powerperformance
Performance
hf.co/unsloth/Qwen… deepseek-coder-v2:…
Tokens/sec21.1117.2
First chunk571 ms275 ms
TTFT571 ms275 ms
Load time4.9 s8.9 s
Memory usage22.7 GB17.9 GB
Memory %18%15%
HW Fit Score Breakdown
hf.co/unsloth/Qwen3.8-2…
Speed
20/50
TTFT
19/20
Memory
30/30
deepseek-coder-v2:16b
Speed
50/50
TTFT
20/20
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
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest