Orionfold/II-Medical-8B-GGUF

II Medical 8B GGUF

GGUF quantizations of Intelligent-Internet/II-Medical-8B, verified end-to-end on the NVIDIA DGX Spark (GB10, 128 GB unified memory).

Spark-tested

Every Orionfold quant ships with a measurement quad on the NVIDIA DGX Spark (GB10, 128 GB unified memory): perplexity, sustained tok/s, thermal envelope, and MedMCQA (n=50, mcq_letter) accuracy. The numbers below are the actual run, not a wishlist.

Variant	Size	Perplexity (wikitext-2)	tok/s on Spark	MedMCQA (n=50, mcq_letter)
Q4_K_M	4.7 GB	16.550	43.6	42.0%
Q5_K_M	5.4 GB	16.242	36.4	52.0%
Q6_K	6.3 GB	16.014	32.8	46.0%
Q8_0	8.1 GB	16.296	28.4	48.0%
F16	15.3 GB	16.268	15.9	48.0%

Thermal envelope: sustained-load minutes before thermal throttle on a single GB10 = 18 min. Beyond this, expect tok/s degradation; the duty-cycle disclosure is per Orionfold's quant-card standard.

Variants

Variant	Recommended use
Q4_K_M	Best balance — fits comfortably in Spark unified memory at 70B; default pick.
Q5_K_M	Higher quality than Q4_K_M with modest size bump.
Q6_K	Near-lossless; recommended if memory headroom allows.
Q8_0	Effectively lossless; reach for this when quality matters more than throughput.
F16	Reference — no quantization. Use only for measurement / baseline.

How to run

Pull a variant:

huggingface-cli download Orionfold/II-Medical-8B-GGUF model-Q5_K_M.gguf \
  --local-dir ./models/ii-medical-8b

Serve it via llama-server (OpenAI-compatible API):

llama-server -m ./models/ii-medical-8b/model-Q5_K_M.gguf \
  -c 4096 -ngl 99 -t 8 \
  --host 0.0.0.0 --port 8080

Or run in-process via llama-cpp-python:

from llama_cpp import Llama
llm = Llama(
    model_path="./models/ii-medical-8b/model-Q5_K_M.gguf",
    n_ctx=4096, n_gpu_layers=99, chat_format="chatml",
)
out = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Summarize the key idea in one paragraph."}],
    temperature=0.0,
)
print(out["choices"][0]["message"]["content"])

LM Studio and Ollama (via a Modelfile) load the GGUF directly with no additional setup.

Methods

Full methodology and Spark-side measurement protocol: Vertical-curator quants on Spark — II-Medical-8B-GGUF + MedMCQA mini-eval.

Other Orionfold vertical curators

Same Spark-tested recipe across the curator-on-Spark series:

• finance-chat-GGUF — AdaptLLM finance-chat (Llama-2-7B lineage) for FinanceBench-shaped queries
• Saul-7B-Instruct-v1-GGUF — Equall Saul-7B legal-instruct for LegalBench-shaped queries
• SecurityLLM-GGUF — Mistral-based cyber-tuned model with CyberMetric mini-eval gating

Each card lists its own measurement quad; the headline numbers are recorded as the actual sweep ran, never pre-corrected.

---

Published by Orionfold LLC · orionfold.com · Methods documented at ainative.business/field-notes.

Want to know when the next Orionfold vertical curator drops? Join the launch list at orionfold.com.