selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

microsoft logo

UserLM-2.0

microsoft·Instruct·released 1 Oct 2026

MIT8B128K ctx ≈6.3 GB
Your GPU
llama-server -hf liodon-ai/UserLM-2.0-imatrix-GGUF:Q4_K_M
All 4 runners ↓

UserLM-2.0 is an 8-billion-parameter user simulator for user-AI conversations. Unlike typical language models trained to play the assistant, UserLM-2.0 generates the user side of a conversation. It is conditioned on a task intent that describes the user's high-level objective.

Notify me when

How much VRAM does UserLM-2.0 need?

At Q4_K_M UserLM-2.0 needs about 6.3 GB with an 8K context (6.3 GB at Q4, 17 GB at full precision). Pick your GPU to see what fits and how fast it runs.

--vram
any
--gpus
--quant

Needs: ≈6.3 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.

Change quant, context or KV cache to compare
Advanced: context 8K · KV cache 16-bit
Context
KV cache

Smallest GPU for each quant and context (KV cache 16-bit)

Quantisation4K8K16K32K64K128K
Q3_K_M
Q4_K_M
Q5_K_M
Q6_K
Q8_0
FP16

≤16 GB card24–32 GB48–96 GBmore

QuantisationQualityWeightsKV cacheTotal
Q2_KHeavy lossSmallest, noticeably worse qualityHeavy loss2.5 GB est.1.0 GB≈4.1 GB
Q3_K_MNoticeable lossSmall, some quality lossNoticeable loss3.7 GB est.1.0 GB≈5.3 GB
Q4_K_MrecommendedSmall lossRecommended default for local useSmall loss4.6 GB file1.0 GB≈6.3 GB
Q5_K_MNear-losslessNear-lossless for most tasksNear-lossless5.3 GB file1.0 GB≈7.1 GB
Q6_KNear-losslessPractically losslessNear-lossless6.1 GB file1.0 GB≈8.0 GB
Q8_0LosslessLossless in practice, twice the size of Q4Lossless8.0 GB file1.0 GB≈9.8 GB
FP16 / BF16LosslessFull precision, as releasedLossless15 GB est.1.0 GB≈17 GB

Estimates for 8K tokens of context: weights + KV cache + runtime overhead. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.

How to pick a quant

Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.

  • LosslessF16, Q8_0
  • Near-losslessQ6_K, Q5_K_M
  • Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
  • Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
  • Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K

Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B

How much context fits?

Model quant
KV cache

At 8K context, Q4_K_M needs ≈6.3 GB(4.6 GB weights + 1.0 GB KV cache + 0.7 GB overhead). Pick a GPU above to see how much context fits.

05101520251K2K4K8K16K32K64K128KGB

Weights + overheadKV cache

Can the RTX 4060 run UserLM-2.0? →

Speed vs quality per quant

Smaller quants run faster and fit in less memory, but lose quality.

Q2_KQ3_K_MQ4_K_MQ5_K_MQ6_KQ8_0F16

Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.

Real-world speed of UserLM-2.0

Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →

No medians yet. Be one of the first 3 to report a setup.

All reports

Run UserLM-2.0 locally

--quantQ4_K_Mdefault; pick your GPU to tailor itliodon-ai/UserLM-2.0-imatrix-GGUF

OpenAI-compatible server with a web UIdocs
llama-server -hf liodon-ai/UserLM-2.0-imatrix-GGUF:Q4_K_M

Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.

Install llama.cpp

Serve an OpenAI-compatible APIdocs
vllm serve microsoft/UserLM-2.0
Smaller FP8 builddocs
vllm serve liodon-ai/UserLM-2.0-FP8
Docker Compose (NVIDIA)docs
yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: microsoft/UserLM-2.0
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 8000.

Install vLLM

Serve an OpenAI-compatible APIdocs
sglang serve microsoft/UserLM-2.0 --host 0.0.0.0 --port 30000
Docker Compose (NVIDIA)docs
yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve microsoft/UserLM-2.0 --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

API on port 30000.

Install SGLang

Chat with the pipeline APIdocs
python
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/UserLM-2.0", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])

Install Transformers

  • Text Generation Inferenceofficial · inference server

Quantised versions and downloads

RepositoryFormatQuantSizeDownloads
liodon-ai/UserLM-2.0-FP8SafetensorsFP8—43
liodon-ai/UserLM-2.0-imatrix-GGUFGGUFIQ2_M2.9 GB762
liodon-ai/UserLM-2.0-imatrix-GGUFGGUFIQ3_M3.8 GB762
liodon-ai/UserLM-2.0-imatrix-GGUFGGUFIQ4_XS4.4 GB762
liodon-ai/UserLM-2.0-imatrix-GGUFGGUFQ4_K_M4.9 GB762
liodon-ai/UserLM-2.0-imatrix-GGUFGGUFQ5_K_M5.7 GB762
liodon-ai/UserLM-2.0-imatrix-GGUFGGUFQ6_K6.6 GB762
liodon-ai/UserLM-2.0-imatrix-GGUFGGUFQ8_08.5 GB762
liodon-ai/UserLM-2.0-GGUFGGUF——369

About UserLM-2.0

UserLM-2.0 is an 8-billion-parameter user simulator for user-AI conversations. Unlike typical language models trained to play the assistant, UserLM-2.0 generates the user side of a conversation. It is conditioned on a task intent that describes the user's high-level objective. UserLM-2.0 can: • Generate an initial user utterance from a task intent. • Generate follow-up user utterances from the conversation so far. • Emit when it determines that the user's objective has • been satisfied and the conversation should end. The model is intended to support research on realistic user simulation and the development and evaluation of more robust assistant models. Paper: The accompanying UserLM-2.0 paper is forthcoming. An arXiv link will be added when it becomes available. • Developed by: Omer Gul (Microsoft Research intern, Spring 2026), • Philippe Laban (Microsoft Research), Tanya Goyal (Microsoft Research), and • Jennifer Neville (Microsoft Research) • Model type: Generative causal language model, 8B parameters • Language: English • License: MIT • Backbone: meta-llama/Llama-3.1-8B-Instruct • Repository: microsoft/UserLM-2.0

Full model card on Hugging Face →

Alternatives to UserLM-2.0

All alternatives →
ornith-ai logo

Ornith-1.0-9B

ornith-ai·Chat

≈6.8 GB

Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.

9B256K ctx MIT
822.7KJun 2026gguf
Qwen logo

Qwen3-8B

Qwen·Chat

≈6.5 GB

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

8.2B40K ctx Apache 2.0
6.1MApr 2025ollama
ornith-ai logo

Ornith-1.5-9B

ornith-ai·Chat

≈7.2 GB

Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

9.7B256K ctx MIT
570.4KAug 2026ollama

NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 is a small language model (SLM) further post-trained from Gemma-4-E4B-it by NVIDIA. This is the full-precision (BF16) release.

8B64K ctx openmdw-1.1
29.7KOct 2026gguf
ibm-granite logo

granite-4.2-8b

ibm-granite·Chat

≈7.0 GB

Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems.

8.8B128K ctx Apache 2.0
59.9KAug 2026ollama
Qwen logo≈5.5 GB

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

7.6B32K ctx Apache 2.0
6.5MSept 2024ollama

UserLM-2.0 FAQ

How much VRAM does UserLM-2.0 need?
About 6.3 GB at Q4_K_M with an 8K context. Q8_0 needs about 9.8 GB and full precision about 17 GB. Longer contexts need more memory for the KV cache.
Can UserLM-2.0 run on the RTX 4060?
Yes. It fits at Q5_K_M (about 7.1 GB), at an estimated 26 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
Can I use UserLM-2.0 commercially?
Yes. It is released under MIT. Permissive: do almost anything as long as you keep the copyright notice.
What is the context length of UserLM-2.0?
131,072 tokens (128K). The full window needs far more memory than an 8K context.
How do I run UserLM-2.0 with llama.cpp?
Run llama-server -hf liodon-ai/UserLM-2.0-imatrix-GGUF:Q4_K_M. It downloads the GGUF and starts an OpenAI-compatible server.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.