Can the Tesla P40 run DeskForge-Gemma4-E4B?
DeskForge-Gemma4-E4B·7.9B·Tesla P40·24 GB VRAM
Yes. The Tesla P40 runs DeskForge-Gemma4-E4B fully in VRAM at FP16 / BF16 (about 16 GB of 24 GB), at roughly 12 tokens/s.
- best quant
- FP16 / BF16
- needs
- 16 GB
- usable
- 24 GB
- est. speed
- ~12 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the DeskForge-Gemma4-E4B page →
Every quantisation of DeskForge-Gemma4-E4B on the Tesla P40
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 5.4 GB | fits | ~73 tok/s |
| Q3_K_M | 5.9 GB | fits | ~49 tok/s |
| Q4_K_M | 6.3 GB | fits | ~40 tok/s |
| Q5_K_M | 6.8 GB | fits | ~34 tok/s |
| Q6_K | 7.2 GB | fits | ~29 tok/s |
| Q8_0 | 9.0 GB | fits | ~23 tok/s |
| FP16 / BF16 pick | 16 GB | fits | ~12 tok/s |
Speed is a bandwidth-based estimate for generating text (347 GB/s); prompt processing and long contexts are slower.
Measured speed on the Tesla P40
No community reports for this pair yet.
Report your own speed →Run DeskForge-Gemma4-E4B on the Tesla P40
Using FP16 / BF16, the best fit for Tesla P40.
ollama run hf.co/mradermacher/DeskForge-Gemma4-E4B-GGUF:F16 llama-server -hf mradermacher/DeskForge-Gemma4-E4B-GGUF:F16Downloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get mradermacher/DeskForge-Gemma4-E4B-GGUF@F16Then load it from the LM Studio app or with `lms load`.
vllm serve docling-project/DeskForge-Gemma4-E4Bservices:
vllm:
image: vllm/vllm-openai:latest
command: docling-project/DeskForge-Gemma4-E4B
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 docling-project/DeskForge-Gemma4-E4B --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve docling-project/DeskForge-Gemma4-E4B --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.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="docling-project/DeskForge-Gemma4-E4B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Vision models that fit the Tesla P40 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8.8B | Q8_0 | ≈10 GBFits in memory | ~20 tok/s | |
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~19 tok/s | |
| 8.3B | Q8_0 | ≈8.9 GBFits in memory | ~22 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~19 tok/s | |
| 4.7B | Q8_0 | ≈5.9 GBFits in memory | ~39 tok/s | |
| 8.7B | Q8_0 | ≈10 GBFits in memory | ~21 tok/s |
Other GPUs that run DeskForge-Gemma4-E4B
Frequently asked questions
- Can the Tesla P40 run DeskForge-Gemma4-E4B?
- Yes. The Tesla P40 runs DeskForge-Gemma4-E4B fully in VRAM at FP16 / BF16 (about 16 GB of 24 GB), at roughly 12 tokens/s.
- How fast does DeskForge-Gemma4-E4B run on the Tesla P40?
- An estimate from memory bandwidth gives about 12 tokens/s at FP16 / BF16.
- Which quantisation of DeskForge-Gemma4-E4B should I use on the Tesla P40?
- 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.