GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

DevDPParikh/sarathi-qwen2.5-0.5b-instruct-GGUF overview

Sarathi GGUF release Upstream: Qwen/Qwen2.5 0.5B Instruct at immutable revision 7ae557604adf67be50417f59c2c2f167def9a775 . Conversion and quantization use llam…

llama.cppgguflicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~400.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
model-q5_k_m.ggufGGUFQ5_K_M400.6 MBDownload
model-q8_0.ggufGGUFQ8_0506.5 MBDownload

Model Details

Model IDDevDPParikh/sarathi-qwen2.5-0.5b-instruct-GGUF
AuthorDevDPParikh
Pipeline
Licenseapache-2.0
Base model
Last modified2026-07-28T04:45:14.000Z

Model README

---

license: apache-2.0

library_name: llama.cpp

---

Sarathi GGUF release

Upstream: Qwen/Qwen2.5-0.5B-Instruct at immutable revision 7ae557604adf67be50417f59c2c2f167def9a775.

Conversion and quantization use llama.cpp revision 99f3dc32296f825fec94f202da1e9fede1e78cf9.

Converted and quantized for Sarathi using llama.cpp.

| Quantization | File | Bytes | SHA-256 | Minimum RAM (MiB) | Recommended RAM (MiB) |

| --- | --- | ---: | --- | ---: | ---: |

| Q5_K_M | model-q5_k_m.gguf | 420086080 | 0ba088dcd4d4ee6a6e74848de340b559157da286780487c3c2c510e6c6197730 | 2816 | 3840 |

| Q8_0 | model-q8_0.gguf | 531068224 | 119b718b660a2778fd31dcb737daf867fcdbf0c027b92d4f4b3fbe6772d74621 | 2816 | 3840 |

Limitations

English-only deterministic MVP qualification. Desktop benchmarks are informational; verify physical-device compatibility separately.

Run DevDPParikh/sarathi-qwen2.5-0.5b-instruct-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models