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.

Axion1-0 logo

Can the NVIDIA H100 SXM 80GB run Axion-1.0-35B?

Axion-1.0-35B·35.1B (3.9B active)·NVIDIA H100 SXM 80GB·80 GB VRAM

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

Yes. The NVIDIA H100 SXM 80GB runs Axion-1.0-35B fully in VRAM at FP16 / BF16 (about 70 GB of 80 GB), at roughly 236 tokens/s.

best quant
FP16 / BF16
needs
70 GB
usable
80 GB
est. speed
~236 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Axion-1.0-35B page →

Every quantisation of Axion-1.0-35B on the NVIDIA H100 SXM 80GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss14 GBfits~1436 tok/s
Q3_K_M Noticeable loss18 GBfits~966 tok/s
Q4_K_M Small loss22 GBfits~779 tok/s
Q5_K_M Near-lossless25 GBfits~664 tok/s
Q6_K Near-lossless29 GBfits~573 tok/s
Q8_0 Lossless37 GBfits~444 tok/s
FP16 / BF16 pickLossless70 GBfits~236 tok/s

Speed is a bandwidth-based estimate for generating text (3350 GB/s); prompt processing and long contexts are slower.

Measured speed on the NVIDIA H100 SXM 80GB

No community reports for this pair yet.

Report your own speed →

Run Axion-1.0-35B on the NVIDIA H100 SXM 80GB

Using Q8_0, the best fit for NVIDIA H100 SXM 80GB.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/mradermacher/Axion-1.0-35B-GGUF:Q8_0
llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf mradermacher/Axion-1.0-35B-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 mradermacher/Axion-1.0-35B-GGUF@Q8_0

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

vLLM · Serve an OpenAI-compatible APIdocs
vllm serve Axion1-0/Axion-1.0-35B
vLLM · Docker Compose (NVIDIA)docs
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: Axion1-0/Axion-1.0-35B
    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 Axion1-0/Axion-1.0-35B --host 0.0.0.0 --port 30000
SGLang · Docker Compose (NVIDIA)docs
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve Axion1-0/Axion-1.0-35B --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="Axion1-0/Axion-1.0-35B", 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 NVIDIA H100 SXM 80GB comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
36BA3BQ8_0≈38 GBFits in memory~578 tok/sCommercial OK
31.2BA4.6BQ8_0≈39 GBFits in memory~376 tok/sCommercial OK
32.8BQ8_0≈37 GBFits in memory~53 tok/sCommercial OK
RecursiveSI logoflintRecursiveSI
39.8BA1.3BQ8_0≈43 GBFits in memory~1387 tok/sCommercial OK
20.9BA4.2BQ8_0≈13 GBFits in memory~414 tok/sCommercial OK
30.5BA3BQ8_0≈33 GBFits in memory~578 tok/sCommercial OK

Other GPUs that run Axion-1.0-35B

Frequently asked questions

Can the NVIDIA H100 SXM 80GB run Axion-1.0-35B?
Yes. The NVIDIA H100 SXM 80GB runs Axion-1.0-35B fully in VRAM at FP16 / BF16 (about 70 GB of 80 GB), at roughly 236 tokens/s.
How fast does Axion-1.0-35B run on the NVIDIA H100 SXM 80GB?
An estimate from memory bandwidth gives about 236 tokens/s at FP16 / BF16.
Which quantisation of Axion-1.0-35B should I use on the NVIDIA H100 SXM 80GB?
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.