From: <huggingface.co/lmstudio-community> Newsgroups: alt.freeweights.phiSubject: Phi-4-reasoning-MLX-4bit Date: 2026-11-15Commit: 83ac684Signed: 2DC28CC7B26A283B ✓ Text generation model with 14.7B parameters. Safetensors weights, 8.26 GB in all. Published by lmstudio-community under MIT.
14.7B params 8.26 GB Phi-4-reasoning-MLX-4bit safetensors permissive Facts Params 14.7B Size 8.26 GB Formats safetensors Task text generation License MIT permissive
fw
$ fw get lmstudio-community/Phi-4-reasoning-MLX-4bit
# manifest sha256 4bff41ab7dad… · 8.26 GB · 12 files
$ fw verify ./Phi-4-reasoning-MLX-4bit lmstudio-community/Phi-4-reasoning-MLX-4bitHosted (signed) lmstudio-community/Phi-4-reasoning-MLX-4bit Last check: 2026-11-15 05:11 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of Phi-4-reasoning .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 8.26 GB
Weights 8.25 GB (safetensors)
Parameters 14.7B
Formats safetensors
Task text generation
License MIT (permissive)
Files 12, each with a sha256
Publisher lmstudio-community
Added 2026-11-15
Section alt.freeweights.phi Lineage
Original release from the publisher.
Base model: microsoft/Phi-4-reasoning
Where these bytes come from
Publisher at the pinned commit →You
Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge Host Last check Result huggingface.co 2026-11-15 05:11 UTC passed
Model card From the publisher at commit
83ac684 . Shown as plain text with links; images open at the publisher.
This model lmstudio-community/Phi-4-reasoning-MLX-4bit was converted to MLX format from microsoft/Phi-4-reasoning using mlx-lm version 0.24.0 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("lmstudio-community/Phi-4-reasoning-MLX-4bit")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True) Files 12 files · 8.26 GB Weights 8.25 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 12 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 1.17 KB e9a9e407b963528776cd55dd4937f406b820cfa9c107e055afca4019a79bcca5 chat_template.jinja 1.77 KB 4e88dcaabb2b09ddb706f789a9ca66bc60dc4cb05fc142ae20b418b46198829e config.json 1.01 KB a7145de545195b593de65697f7d00c4cd952627e6598860c4eedbb7e253af2a5 merges.txt 917 KB b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502 model-00001-of-00002.safetensors 5.31 GB 7feaddae53c2d5dc27c50962596eac6db61cdc03a1f376612717db3801f582f5 model-00002-of-00002.safetensors 2.94 GB dae49fc6251fdabd1ba6e5d0188743ea44a0a0a8af669c3060da21072f52bd45 model.safetensors.index.json 49.3 KB 776a5f4af5e7ed3f3f7ec8321f0614a9e81d3ed34d5b4e446b73d7e0270bed8a special_tokens_map.json 570 B f1709cc2511788dd182569aa4071b845ac5df22a9424712dd7e456783be74be3 tokenizer.json 7.15 MB 98fe258b0c1e42a10a9c3b5692ba081d40c177da924800c4f034ad940f794ff9 tokenizer_config.json 19.3 KB 829f3d467fd667b75d8168f2283e91425b6eefd3f34f336a5d24bdf5147b8e00 vocab.json 1.61 MB 23b80b3c4932a7733eb91487cb2fdbc56c5bd199a459128f538095a36dad5287
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 83ac684bce pinned now 2026-11-15 05:11 UTC 12 files · 8.26 GB
Use it fw
$ fw get lmstudio-community/Phi-4-reasoning-MLX-4bit
# manifest sha256 4bff41ab7dad… · 8.26 GB · 12 files
$ fw verify ./Phi-4-reasoning-MLX-4bit lmstudio-community/Phi-4-reasoning-MLX-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/lmstudio-community/Phi-4-reasoning-MLX-4bit.json --dir ./Phi-4-reasoning-MLX-4bit
$ python3 fw.py verify ./Phi-4-reasoning-MLX-4bit ./lmstudio-community__Phi-4-reasoning-MLX-4bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download lmstudio-community/Phi-4-reasoning-MLX-4bit --revision 83ac684bce36aec035ff73dc155611161104ca67 --local-dir ./Phi-4-reasoning-MLX-4bittransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("lmstudio-community/Phi-4-reasoning-MLX-4bit", revision="83ac684bce36aec035ff73dc155611161104ca67")
model = AutoModelForCausalLM.from_pretrained("lmstudio-community/Phi-4-reasoning-MLX-4bit", revision="83ac684bce36aec035ff73dc155611161104ca67", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve lmstudio-community/Phi-4-reasoning-MLX-4bit --revision 83ac684bce36aec035ff73dc155611161104ca67License Name MIT License Id MIT Class Permissive Redistribution yes Listing Hosted (signed) Decided License as declared by the publisher. No person read it. 2026-11-15 Text in README.md Text sha256 e9a9e407b963528776cd55dd4937f406b820cfa9c107e055afca4019a79bcca5 Terms gate No extra terms beyond the license. Read the license text
Licenses are checked against the license table . A custom license passes only after a person reads it.
Provenance From: <huggingface.co/lmstudio-community> Newsgroups: alt.freeweights.phiSubject: Phi-4-reasoning-MLX-4bit Date: 2026-11-15Commit: 83ac684Signed: 2DC28CC7B26A283B ✓ How to verify
$ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/Phi-4-reasoning-MLX-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/Phi-4-reasoning-MLX-4bit.json.minisig
$ minisign -Vm Phi-4-reasoning-MLX-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download
Model tree No model in the catalog names this one as its parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download lmstudio-community/Phi-4-reasoning-MLX-4bitOpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
phi 400 MB bunny-phi-2-siglip-lora safetensors permissive Facts Params not stated Size 400 MB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/BAAI> Subject: bunny-phi-2-siglip-lora 3.8B params 7.64 GB MediPhi safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi 3.8B params 7.64 GB MediPhi-Clinical safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-Clinical 3.8B params 7.64 GB MediPhi-Guidelines safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-Guidelines 3.8B params 7.64 GB MediPhi-Instruct safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-Instruct 3.8B params 7.64 GB MediPhi-MedCode safetensors permissive Facts Params 3.8B Size 7.64 GB Formats safetensors Task text generation License MIT permissive flip From: <huggingface.co/microsoft> Subject: MediPhi-MedCode
lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.phiSubject: 
BAAI