Model Intelligence Sheet
mradermacher/armory-coder-3b-merged-GGUF overview
< quantize version: 2 < output tensor quantised: 1 < convert type: hf < vocab type: < tags: < quants: x f16 Q4 K S Q2 K Q8 0 Q6 K Q3 K M Q3 K S Q3 K L Q4 K M Q…
Runs locally from ~1.19 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
12 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| armory-coder-3b-merged.IQ4_XS.gguf | GGUF | GGUF | 1.63 GB | Download |
| armory-coder-3b-merged.Q2_K.gguf | GGUF | GGUF | 1.19 GB | Download |
| armory-coder-3b-merged.Q3_K_L.gguf | GGUF | GGUF | 1.59 GB | Download |
| armory-coder-3b-merged.Q3_K_M.gguf | GGUF | GGUF | 1.48 GB | Download |
| armory-coder-3b-merged.Q3_K_S.gguf | GGUF | GGUF | 1.35 GB | Download |
| armory-coder-3b-merged.Q4_K_M.gguf | GGUF | GGUF | 1.80 GB | Download |
| armory-coder-3b-merged.Q4_K_S.gguf | GGUF | GGUF | 1.71 GB | Download |
| armory-coder-3b-merged.Q5_K_M.gguf | GGUF | GGUF | 2.07 GB | Download |
| armory-coder-3b-merged.Q5_K_S.gguf | GGUF | GGUF | 2.02 GB | Download |
| armory-coder-3b-merged.Q6_K.gguf | GGUF | GGUF | 2.36 GB | Download |
| armory-coder-3b-merged.Q8_0.gguf | GGUF | GGUF | 3.06 GB | Download |
| armory-coder-3b-merged.f16.gguf | GGUF | GGUF | 5.75 GB | Download |
Model Details
| Model ID | mradermacher/armory-coder-3b-merged-GGUF |
|---|---|
| Author | mradermacher |
| Pipeline | — |
| License | — |
| Base model | — |
| Last modified | 2026-07-06T06:58:29.000Z |
Model README
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/gorgodev88/armory-coder-3b-merged
Run mradermacher/armory-coder-3b-merged-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models