Instructions to use ConeML/coneml-810m-alpha-arithmetic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ConeML/coneml-810m-alpha-arithmetic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ConeML/coneml-810m-alpha-arithmetic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ConeML/coneml-810m-alpha-arithmetic")
model = AutoModelForCausalLM.from_pretrained("ConeML/coneml-810m-alpha-arithmetic", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ConeML/coneml-810m-alpha-arithmetic with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0
# Run inference directly in the terminal:
llama cli -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0
# Run inference directly in the terminal:
llama cli -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ConeML/coneml-810m-alpha-arithmetic:Q8_0

Use Docker

docker model run hf.co/ConeML/coneml-810m-alpha-arithmetic:Q8_0

LM Studio
Jan

vLLM

How to use ConeML/coneml-810m-alpha-arithmetic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ConeML/coneml-810m-alpha-arithmetic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ConeML/coneml-810m-alpha-arithmetic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ConeML/coneml-810m-alpha-arithmetic:Q8_0

SGLang

How to use ConeML/coneml-810m-alpha-arithmetic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ConeML/coneml-810m-alpha-arithmetic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ConeML/coneml-810m-alpha-arithmetic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ConeML/coneml-810m-alpha-arithmetic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ConeML/coneml-810m-alpha-arithmetic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ConeML/coneml-810m-alpha-arithmetic with Ollama:
```
ollama run hf.co/ConeML/coneml-810m-alpha-arithmetic:Q8_0
```

Unsloth Studio

How to use ConeML/coneml-810m-alpha-arithmetic with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ConeML/coneml-810m-alpha-arithmetic to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ConeML/coneml-810m-alpha-arithmetic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ConeML/coneml-810m-alpha-arithmetic to start chatting

Docker Model Runner
How to use ConeML/coneml-810m-alpha-arithmetic with Docker Model Runner:
```
docker model run hf.co/ConeML/coneml-810m-alpha-arithmetic:Q8_0
```

Lemonade

How to use ConeML/coneml-810m-alpha-arithmetic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ConeML/coneml-810m-alpha-arithmetic:Q8_0

Run and chat with the model

lemonade run user.coneml-810m-alpha-arithmetic-Q8_0

List all available models

lemonade list

Atomic Chat

coneml-810m-alpha-arithmetic / eval /PEER_COMPARISON.md

RandomMountainMan

Clarify 810M family naming

352376e verified 20 days ago

preview code

Raw

History Blame Contribute Delete

7.41 kB

ConeML 810M peer diagnostic and resource context

Date: 2026-07-30

This is an interface-specific diagnostic screen, not a neutral ranking of general model capability. Each instruction-tuned model was evaluated through its own instruction interface. All models used greedy decoding with repetition penalty 1.15. Arithmetic and function-writing used matched short-answer generation budgets.

The task families match ConeML's supervised training surfaces. That gives the comparison practical value for locating the release's envelope, but it also means these results must not be generalized to unrelated tasks. Standard GSM8K and HumanEval results remain separately disclosed in the model cards.

Instruct-model results

measured surface	ConeML 810M Alpha	ConeML 810M Alpha-Arithmetic	Qwen3.5 0.8B	Qwen3 0.6B	Llama 3.2 1B Instruct	TinyLlama Chat	SmolLM2 1.7B Instruct
mixed arithmetic screen (n=585)	421 (72.0%)	442 (75.6%)	154 (26.3%)	223 (38.1%)	343 (58.6%)	113 (19.3%)	380 (65.0%)
four core arithmetic lanes (n=225)	177 (78.7%)	221 (98.2%)	150 (66.7%)	208 (92.4%)	221 (98.2%)	92 (40.9%)	221 (98.2%)
executed single functions (n=100)	83	35	93	98	79	51	96
transitive names, depth 1/3/5 (n=32 each)	23/15/15	26/17/16	23/22/10	18/10/9	16/7/5	8/18/22	16/6/5
transitive entities, depth 1/3/5 (n=32 each)	15/11/10	16/11/12	18/16/14	14/17/11	0/6/7	14/15/11	22/21/10
designated-refusal prompts (n=17)	13	11	0	1	1	0	1
over-refusals on contrasts (n=5)	0	0	0	0	0	0	0

The honest result is mixed:

At matched short-answer budgets, the ConeML pair led this post-trained peer group on the broader arithmetic screen.
On the four core arithmetic lanes, the Arithmetic variant tied Llama 3.2 Instruct and SmolLM2 at this reduced sample size. Its separate full-size internal result is 1,093/1,116 (97.9%).
ConeML 810M Alpha exceeded Llama 3.2 Instruct and TinyLlama Chat on the executed function screen, but Qwen3.5, Qwen3, and SmolLM2 scored higher.
On name-chain transitive selection, ConeML 810M Alpha-Arithmetic recorded 26/32, 17/32, and 16/32 at depths 1, 3, and 5. It exceeded Qwen3 and Llama 3.2 at all three shown depths and exceeded Qwen3.5 at depths 1 and 5; Qwen3.5 led it at depth 3, and TinyLlama led the group at depth 5.
Entity-chain transfer was mixed: ConeML 810M Alpha recorded 15/11/10 and ConeML 810M Alpha-Arithmetic 16/11/12 at depths 1/3/5, while different peers led each depth. Chance is 1/(depth+1). The non-monotonic peer rows reinforce that this is an exact-selection surface test, not proof of general reasoning depth.
The refusal row measures a trained response policy on designated prompts, not factual correctness or general epistemic calibration.

The peer-harness refusal results above differ from the dedicated ConeML probe's 17/17 for each release because the generation loops differ. Both measurements are reported rather than merged.

Qwen3.5 thinking-mode sensitivity

Qwen3.5 0.8B was also evaluated with thinking enabled on the same 585 arithmetic items:

metric	Qwen3.5 thinking	Qwen3.5 short-answer	ConeML 810M Alpha-Arithmetic short-answer
accuracy	451/585 (77.1%)	154/585 (26.3%)	442/585 (75.6%)
generated tokens per item	mean 844; median 699	at most 48	at most 48
p95 / generation cap	1,536 / 1,536	48 / 48	48 / 48
truncation rate	138/585 (23.6%)	approximately 0%	approximately 0%
mean wall time per item	2.43 s	approximately 0.1 s	approximately 0.1 s
correct answers per 1,000 generated tokens	0.91	5.5	approximately 15.7 or higher

Thinking mode recovered Qwen3.5 to statistical parity with ConeML 810M Alpha-Arithmetic on this screen, while using at least 17.6 times the per-answer generation budget and approximately 24 times the measured wall time. Wall-time ratios are specific to the recorded hardware, batching, and implementation. This is an inference-cost comparison, not a claim that thinking mode is intrinsically inferior.

Against-interest base result

On the same 585 arithmetic items, through a task frame native to neither base model, Qwen3.5 0.8B Base scored 492/585 (84.1%), while ConeML base checkpoint 188 scored 156/585 (26.7%). This result is included because it prevents an absolute-superiority reading: high-exposure base models may already contain strong task-formatted behavior, and post-training can move capability between output surfaces.

Training-resource context

ConeML's selected base consumed approximately 12.32B token positions: 15.2 tokens per parameter and approximately 5.99e19 training FLOPs under the 6 × parameters × tokens convention.

model family	disclosed pretraining tokens	approximate tokens/parameter	approximate training FLOPs vs ConeML
ConeML 810M	12.32B	15.2	1×
TinyLlama 1.1B	3T	2,727	330×
Llama 3.2 1B	up to 9T	7,258	1,118×, plus distillation
SmolLM2 1.7B	11T	6,471	1,873×
Qwen3 0.6B	36T	60,000	2,164×
Qwen3.5 0.8B	not disclosed	not stated	not stated

These are estimated pretraining FLOP ratios, not historical electricity or monetary costs for the peer models.

ConeML pretraining took approximately 11 days on one local RTX 5090. At an explicitly assumed average wall draw of 0.70 kW, that corresponds to 184.8 kWh. Applying an assumed Swiss residential tariff range of CHF 0.14–0.30/kWh gives approximately CHF 26–55 of marginal pretraining electricity.

ConeML pretraining unit	estimate
average throughput	12,963 token positions/s
wall time per billion token positions	21.4 h
energy per billion token positions	15.0 kWh
energy per million token positions	15 Wh
estimated wall energy per token position	0.054 J
marginal electricity per billion token positions	CHF 2.10–4.50

The energy and cost figures are estimates derived from the stated power and tariff assumptions, not meter readings. They exclude hardware, depreciation, labor, supervised fine-tuning, evaluation, conversion, datacenter PUE, and carbon intensity. No emissions claim is made.

Evaluated revisions

Qwen/Qwen3.5-0.8B@2fc06364715b967f1860aea9cf38778875588b17
Qwen/Qwen3-0.6B@c1899de289a04d12100db370d81485cdf75e47ca
unsloth/Llama-3.2-1B-Instruct@5a8abab4a5d6f164389b1079fb721cfab8d7126c
TinyLlama/TinyLlama-1.1B-Chat-v1.0@fe8a4ea1ffedaf415f4da2f062534de366a451e6
HuggingFaceTB/SmolLM2-1.7B-Instruct@31b70e2e869a7173562077fd711b654946d38674

The exact aggregates are in peer-comparison-summary.json. Complete generation rows are retained privately; their frozen SHA-256 commitments are published in PEER_EVIDENCE_SHA256SUMS.txt.

Primary resource disclosures

Qwen3 pretraining: Qwen3 release post
Llama 3.2 token count and distillation: Meta Llama 3.2 model card
TinyLlama token count: TinyLlama model card
SmolLM2 token count: Hugging Face SmolLM2 model card