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.

XHToken logo

Can the RTX 3060 12GB run Spark-X2.6-1.7B?

Spark-X2.6-1.7B·1.7B·GeForce RTX 3060 12GB·12 GB VRAM

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

Yes. The RTX 3060 12GB runs Spark-X2.6-1.7B fully in VRAM at FP16 / BF16 (about 4.3 GB of 12 GB), at roughly 58 tokens/s.

best quant
FP16 / BF16
needs
4.3 GB
usable
12 GB
est. speed
~58 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Spark-X2.6-1.7B page →

Every quantisation of Spark-X2.6-1.7B on the RTX 3060 12GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss1.5 GBfits~353 tok/s
Q3_K_M Noticeable loss1.8 GBfits~237 tok/s
Q4_K_M Small loss2.7 GBfits~191 tok/s
Q5_K_M Near-lossless2.1 GBfits~163 tok/s
Q6_K Near-lossless2.3 GBfits~141 tok/s
Q8_0 Lossless2.7 GBfits~109 tok/s
FP16 / BF16 pickLossless4.3 GBfits~58 tok/s

Speed is a bandwidth-based estimate for generating text (360 GB/s); prompt processing and long contexts are slower.

Measured speed on the RTX 3060 12GB

No community reports for this pair yet.

Report your own speed →

Run Spark-X2.6-1.7B on the RTX 3060 12GB

Using Q8_0, the best fit for RTX 3060 12GB.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/XHToken/Spark-X2.6-1.7B-GGUF:Q8_0
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf XHToken/Spark-X2.6-1.7B-GGUF:Q8_0

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

LM Studio · Download with the lms CLIdocs
lms get XHToken/Spark-X2.6-1.7B-GGUF@Q8_0

Then load it from the LM Studio app or with `lms load`.

SGLang · Serve an OpenAI-compatible APIdocs
sglang serve XHToken/Spark-X2.6-1.7B --host 0.0.0.0 --port 30000
SGLang · Docker Compose (NVIDIA)docs
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve XHToken/Spark-X2.6-1.7B --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="XHToken/Spark-X2.6-1.7B", 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 3060 12GB comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
LiquidAI logoLFM3-1.7BLiquidAI
1.7BQ8_0≈2.7 GBFits in memory~108 tok/sConditions
1.5BQ8_0≈2.6 GBFits in memory~121 tok/sCommercial OK
2BQ8_0≈3.2 GBFits in memory~92 tok/sCommercial OK
1.2BQ8_0≈2.0 GBFits in memory~151 tok/sConditions
1BQ8_0≈1.8 GBFits in memory~186 tok/sConditions
2.5BQ8_0≈3.5 GBFits in memory~74 tok/sCommercial OK

Other GPUs that run Spark-X2.6-1.7B

Frequently asked questions

Can the RTX 3060 12GB run Spark-X2.6-1.7B?
Yes. The RTX 3060 12GB runs Spark-X2.6-1.7B fully in VRAM at FP16 / BF16 (about 4.3 GB of 12 GB), at roughly 58 tokens/s.
How fast does Spark-X2.6-1.7B run on the RTX 3060 12GB?
An estimate from memory bandwidth gives about 58 tokens/s at FP16 / BF16.
Which quantisation of Spark-X2.6-1.7B should I use on the RTX 3060 12GB?
FP16 / BF16: 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.