microsoft

Phi-4-mini-instruct

3.8B parameters · Instruct · Phi family

Long context — how it uses memory →
mit hash verified source matched revision pinned

Which version should I download?

Default pick: GGUF · Q4_K_M — Balanced size/quality — good default.

Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.

Set your rig

Quantizations

Why these quants? Which quant should I pick? What do these mean?

GGUF · Q4_K_M

2.32 GB

Set your rig
Est. speed
—
Swarm
2S / 0L webseed OK

Balanced size/quality — good default.

Magnet .torrent

GGUF · Q8_0

3.80 GB

Set your rig
Est. speed
—
Swarm
2S / 0L webseed OK

Bartowski Q8_0 quant of Phi-4-mini-instruct (3.836B dense) — high-quality option. MIT.

Magnet .torrent

Want a different quant? Request it on the board →

Runs fully on

RTX 5090 · Q8_0 RTX 5060 Ti 16GB · Q8_0 RTX 5070 Ti · Q8_0 RTX 5080 · Q8_0 RTX 5070 · Q8_0

Green = the model's best quant fits fully in GPU/unified memory at 8K context. Tap a card for its full "what runs on it" page.

Context

Advertised 128k · usable ≈ 128k (reported — model card)

How we know

Evidence grade: reported — a maintainer claim with no independent evaluation.

Card: 128K context via LongRoPE. Tech report describes the mechanism but discloses no numeric long-context scores.

Reviewed on Jul 18, 2026.

Capabilities (as declared by the maintainer): tool calling

Run it

Runtime completeness (Q4_K_M torrent): llama.cpp ✅ Ollama – vision sidecar –

  • – Ollama — runs the GGUF directly; no Modelfile bundled
  • – vision sidecar — not a vision model

Context / KV 8,192 tokens · FP16 set above the quant table

Generic commands (no rig set). GPU-offload values assume the model fits on your GPU — set your rig for values tuned to your hardware.

Start the server 
llama-server -m Phi-4-mini-instruct-Q4_K_M.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt.

Save as Modelfile next to the GGUF (Modelfile) 
FROM ./Phi-4-mini-instruct-Q4_K_M.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999
PARAMETER stop "<|endoftext|>"
PARAMETER stop "<|end|>"
# Chat template: Ollama uses the template embedded in the GGUF (no TEMPLATE directive needed).
Create 
ollama create microsoft-phi-4-mini-instruct -f Modelfile
Run 
ollama run microsoft-phi-4-mini-instruct

GGUF is not a first-class vLLM format.

vLLM GGUF support is experimental and single-file only; prefer safetensors/GPTQ/AWQ for production. If you must, pass the .gguf path to `vllm serve` with --load-format gguf on a recent vLLM.

transformers does not load GGUF weights.

GGUF weights run under llama.cpp, Ollama or LM Studio.

Load Phi-4-mini-instruct-Q4_K_M.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).

MLX runs MLX-format weights only (Apple Silicon). This quant is a GGUF build.

GGUF weights run under llama.cpp, Ollama or LM Studio.

Technical details

Chat template

{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}

Stop strings

<|endoftext|> <|end|>

Evidence & provenance

Source

Provenance
https://huggingface.co/microsoft/Phi-4-mini-instruct
Revision pin
cfbefacb99257ffa30c83adab238a50856ac3083
Manifest
Present

License

Name
mit
Commercial use
yes
Access
Open

How verification works →

File hashes (SHA-256)

  • phi-4-mini-instruct-q4-k-m/LICENSE 7df20dcdf9197e9945c14858d41c60f11b52b93e5b69e2b63416b874d598d322
  • phi-4-mini-instruct-q4-k-m/Phi-4-mini-instruct-Q4_K_M.gguf 88c00229914083cd112853aab84ed51b87bdf6b9ce42f532d8c85c7c63b1730a
  • phi-4-mini-instruct-q4-k-m/README.md 60aca40771f3c5eda04387117e45ba9c32f9941369afffc466cc9e0b7dfc789b
  • phi-4-mini-instruct-q8-0/LICENSE 7df20dcdf9197e9945c14858d41c60f11b52b93e5b69e2b63416b874d598d322
  • phi-4-mini-instruct-q8-0/README.md 60aca40771f3c5eda04387117e45ba9c32f9941369afffc466cc9e0b7dfc789b
  • phi-4-mini-instruct-q8-0/microsoft_Phi-4-mini-instruct-Q8_0.gguf a12f242c4ee379b9da91673e5d78b30bfacfe4fd86a0b2259d2ecad5d93cb6c7

Explore further

Appears in

What runs on 6 GB of VRAM What runs on 8 GB of VRAM What runs on a 8 GB Mac Coding models that fit 6 GB Coding models that fit 8 GB Writing models that fit 6 GB

Also consider

Get an email when a better quant fits your rig.

Set your rig once; we'll alert you when a new or better-fitting build lands.

Set your rig

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard
Community

Reviews, sampler presets and community runtime reports. Be the first to contribute.

Reviews (0)

Log in to write a structured review of this model.

No reviews yet.

Sampler presets

Log in to share a sampler preset or vote on presets.

No presets yet.

Community runtime reports

Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.

Log in to report whether a quant loads in your runtime.

No community reports yet.

selected to compare · pick at least 2

Compare ()