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

Can the RTX 4060 run UserLM-2.0?

UserLM-2.0·8B·GeForce RTX 4060·8 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The RTX 4060 runs UserLM-2.0 fully in VRAM at Q5_K_M (about 7.1 GB of 8.0 GB), at roughly 26 tokens/s.

best quant
Q5_K_M
needs
7.1 GB
usable
8.0 GB
est. speed
~26 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the UserLM-2.0 page →

Every quantisation of UserLM-2.0 on the RTX 4060

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.1 GBfits~57 tok/s
Q3_K_M Noticeable loss5.3 GBfits~38 tok/s
Q4_K_M Small loss6.3 GBfits~31 tok/s
Q5_K_M pickNear-lossless7.1 GBfits~26 tok/s
Q6_K Near-lossless8.0 GBtight~23 tok/s
Q8_0 Lossless9.8 GBoffload~11 tok/s
FP16 / BF16 Lossless17 GBoffload~3.2 tok/s

Speed is a bandwidth-based estimate for generating text (272 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 4060

No community reports for this pair yet.

Report your own speed →

Run UserLM-2.0 on the RTX 4060

Using Q5_K_M, the best fit for RTX 4060.

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf liodon-ai/UserLM-2.0-imatrix-GGUF:Q5_K_M

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve microsoft/UserLM-2.0
vLLM · Smaller FP8 builddocs
vllm serve liodon-ai/UserLM-2.0-FP8
vLLM · Docker Compose (NVIDIA)docs
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.

SGLang · Serve an OpenAI-compatible APIdocs
sglang serve microsoft/UserLM-2.0 --host 0.0.0.0 --port 30000
SGLang · Docker Compose (NVIDIA)docs
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.

Transformers · Chat with the pipeline APIdocs
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"])

Chat models that fit the RTX 4060 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8BQ5_K_M≈7.1 GBFits in memory~26 tok/sConditions
8.2BQ5_K_M≈7.3 GBFits in memory~26 tok/sCommercial OK
8BQ5_K_M≈7.1 GBFits in memory~26 tok/sConditions
7.6BQ6_K≈7.0 GBFits in memory~24 tok/sCommercial OK
9.4BQ4_K_M≈7.2 GBFits in memory~26 tok/sCommercial OK
7.2BQ6_K≈7.3 GBFits in memory~25 tok/sCommercial OK

Other GPUs that run UserLM-2.0

Frequently asked questions

Can the RTX 4060 run UserLM-2.0?
Yes. The RTX 4060 runs UserLM-2.0 fully in VRAM at Q5_K_M (about 7.1 GB of 8.0 GB), at roughly 26 tokens/s.
How fast does UserLM-2.0 run on the RTX 4060?
An estimate from memory bandwidth gives about 26 tokens/s at Q5_K_M.
Which quantisation of UserLM-2.0 should I use on the RTX 4060?
Q5_K_M: the largest one that fits. Expected quality: near-lossless compared with the full-precision weights.

Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.