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.

ibm-granite logo

Can the RTX 4070 run granite-4.1-8b-llmon-preview?

granite-4.1-8b-llmon-preview·8.8B·GeForce RTX 4070·12 GB VRAM

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

Yes. The RTX 4070 runs granite-4.1-8b-llmon-preview fully in VRAM at Q8_0 (about 11 GB of 12 GB), at roughly 30 tokens/s.

best quant
Q8_0
needs
11 GB
usable
12 GB
est. speed
~30 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the granite-4.1-8b-llmon-preview page →

Every quantisation of granite-4.1-8b-llmon-preview on the RTX 4070

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.6 GBfits~96 tok/s
Q3_K_M Noticeable loss6.0 GBfits~65 tok/s
Q4_K_M Small loss7.0 GBfits~52 tok/s
Q5_K_M Near-lossless7.9 GBfits~44 tok/s
Q6_K Near-lossless8.8 GBfits~38 tok/s
Q8_0 pickLossless11 GBfits~30 tok/s
FP16 / BF16 Lossless19 GBoffload~4.2 tok/s

Speed is a bandwidth-based estimate for generating text (504 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 4070

No community reports for this pair yet.

Report your own speed →

Run granite-4.1-8b-llmon-preview on the RTX 4070

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve ibm-granite/granite-4.1-8b-llmon-preview
vLLM · Smaller FP8 builddocs
vllm serve liodon-ai/granite-4.1-8b-llmon-preview-FP8
vLLM · Docker Compose (NVIDIA)docs
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: ibm-granite/granite-4.1-8b-llmon-preview
    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 ibm-granite/granite-4.1-8b-llmon-preview --host 0.0.0.0 --port 30000
SGLang · Docker Compose (NVIDIA)docs
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve ibm-granite/granite-4.1-8b-llmon-preview --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="ibm-granite/granite-4.1-8b-llmon-preview", 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 4070 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
8.2BQ8_0≈10 GBFits in memory~32 tok/sCommercial OK
8BQ8_0≈9.8 GBFits in memory~32 tok/sConditions
8BQ8_0≈9.8 GBFits in memory~32 tok/sConditions
7.6BQ8_0≈8.9 GBFits in memory~34 tok/sCommercial OK
9.4BQ8_0≈11 GBFits in memory~28 tok/sCommercial OK
9.2BQ6_K≈11 GBFits in memory~36 tok/sConditions

Other GPUs that run granite-4.1-8b-llmon-preview

Frequently asked questions

Can the RTX 4070 run granite-4.1-8b-llmon-preview?
Yes. The RTX 4070 runs granite-4.1-8b-llmon-preview fully in VRAM at Q8_0 (about 11 GB of 12 GB), at roughly 30 tokens/s.
How fast does granite-4.1-8b-llmon-preview run on the RTX 4070?
An estimate from memory bandwidth gives about 30 tokens/s at Q8_0.
Which quantisation of granite-4.1-8b-llmon-preview should I use on the RTX 4070?
Q8_0: the largest one that fits. Expected quality: 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.