Phi-3.5-mini-instruct-GGUF
Can I run Phi-3.5-mini-instruct-GGUF on my computer?
It depends on your memory, processor, file format and runtime. Hugging Bay offers 1 hosted file; check the file list for the exact selection. A file-size fit is an estimate, not a successful run or speed promise. Read the license before use.
Phi-3.5-mini-instruct-GGUF is an open-weights language model for text generation. Model weights are learned parameters; a runtime loads them. A hosted file is an individual file Hugging Bay can serve. SHA-256 identifies exact file bytes. The availability date above applies to this file record, not the upstream metadata update date.
As of the recorded file availability check on .
Recorded SHA-256 for Phi-3.5-mini-instruct.Q4_K_M.gguf: 3ef532675b6684b28e0a1a0dca8b3bf4132673bf2294b7d87b41b1d64bb03bca. Exact file evidence · Machine-readable source facts · Run evidence and any recorded receipts. A checksum fingerprints only the named file bytes; it does not prove safety, quality, a complete multi-file selection or a successful run.
Updated · Page-copy source revision 8871bab84e1cf80aea1686a944ec335078a6c036 · Source files: apps/web/lib/model-page-template.mjs, apps/web/lib/model-page-v3.mjs, apps/web/lib/aeo-page.mjs · Full revision record
Model metadata: As of at the model source. Popularity counters are source-reported, not measured by Hugging Bay. Availability checked .
Try browser chat with a small demo model (a separate model; device support is checked before loading).
QuantFactory/Phi-3.5-mini-instruct-GGUFProof Lab tested runs
Open a tested command to copy it. Check its paths and settings before running it in your terminal.
Measured on the hardware below. Other machines and answer quality are untested.
Phi-3.5-mini-instruct.Q4_K_M.gguf
llama.cpp server · apple-m4-16gb
· llama.cpp b11630
- Answer starts in
- 0.10 s
- Answer speed
- 37.1 tokens/s
- Peak process memory
- 3.83 GiB
Timed from the request after the server was ready.
Tested command
'/Volumes/Crucial X9/clawd/hb-mac-measurements-20261022/llama-b11630/llama-server' -m results/run-3ef532675b6684b28e0a1a0dca8b3bf4132673bf2294b7d87b41b1d64bb03bca/Phi-3.5-mini-instruct.Q4_K_M.gguf -c 4096 --host 127.0.0.1 --port 18767 -ngl 99 --parallel 1 --cache-ram 0 --reasoning off --verbosity 4 --reasoning-budget 0
curl -sS -N http://127.0.0.1:18767/v1/chat/completions -H 'Content-Type: application/json' -d '{"messages": [{"role": "user", "content": "Explain why the sky is blue in four complete sentences."}], "max_tokens": 128, "temperature": 0, "stream": true, "stream_options": {"include_usage": true}}'Recorded on the lab host above. Review paths and settings before running.
Measurement details
Time to first token (TTFT): request-to-first-content-after-server-ready. Answer speed: runner-eval. Peak memory scope: darwin-time-max-child-high-water-rss-bytes-including-model-load. Memory is shown in gibibytes (GiB).
4096 context tokens. Chat template: passed.
File fingerprint
SHA-256: 3ef532675b6684b28e0a1a0dca8b3bf4132673bf2294b7d87b41b1d64bb03bca