SAVRN
Search Contact SAVRN

Open-weight model · Text generation

SMOLM2Prover-GGUF

by Convergent Intelligence reaperdoesntknow/SMOLM2Prover-GGUF

GGUF quantized version of the SMOLM2Prover model for use with llama.cpp and compatible runtimes. Create a Modelfile: 1. Download SMOLM2Prover-Q4KM.gguf 3. Load and chat!

Parameters—
Context—
Weights996.1 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads2.3k

Model Card

By Convergent Intelligence, published under apache-2.0, revision b44095c04c83.

GGUF quantized version of the SMOLM2Prover model for use with llama.cpp and compatible runtimes. Create a Modelfile: 1. Download SMOLM2Prover-Q4KM.gguf 3. Load and chat! The Q4KM quantization uses: This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model should produce and what it actually produces. DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as structural signals that reveal the geometry of the…

Read Convergent Intelligence's full model card

SMOLM2Prover - GGUF Format

GGUF quantized version of the SMOLM2Prover model for use with llama.cpp and compatible runtimes.

Model Details

  • Original Model: reaperdoesntknow/SMOLM2Prover
  • Architecture: LlamaForCausalLM
  • Context Length: 8192 tokens
  • Embedding Dimension: 960
  • Layers: 32
  • Head Count: 15 (Q), 5 (KV) - GQA

Available Files

File Size Quantization Quality
SMOLM2Prover.gguf 692M F16 Original (no quantization)
SMOLM2Prover-Q4_K_M.gguf 258M Q4_K_M Recommended (good quality/size balance)

Usage

With llama.cpp

# Run with the quantized model
./llama-cli -m SMOLM2Prover-Q4_K_M.gguf -p "Your prompt here" -n 256

With Ollama

Create a Modelfile:

FROM ./SMOLM2Prover-Q4_K_M.gguf

Then:

ollama create smolm2prover -f Modelfile
ollama run smolm2prover

With LM Studio

  1. Download SMOLM2Prover-Q4_K_M.gguf
  2. Place in LM Studio models folder
  3. Load and chat!

Quantization Details

The Q4_K_M quantization uses: - Q4_K for most weights - Q5_0 fallback for tensors not divisible by 256 - Q6_K/Q8_0 for some critical layers

Size reduction: 692M → 258M (63% smaller) BPW: 5.94 bits per weight

Discrepancy Calculus Foundation

This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model should produce and what it actually produces.

DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as structural signals that reveal the geometry of the learning problem. Key concepts:

  • Discrepancy Operator (D): Measures the gap between expected and observed behavior at each training step
  • Jump Sets: Boundaries where model behavior changes discontinuously — these are features, not bugs
  • Ghost Imprinting: Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal

For the full mathematical treatment, see Discrepancy Calculus: Foundations and Core Theory (DOI: 10.57967/hf/8194).

Citation chain: Structure Over Scale (DOI: 10.57967/hf/8165) → Three Teachers to Dual Cognition (DOI: 10.57967/hf/8184) → Discrepancy Calculus (DOI: 10.57967/hf/8194)

License

Same as the original model.

Convergent Intelligence Portfolio

Part of the Standalone Models by Convergent Intelligence LLC: Research Division

Related Models

Model Downloads Format
SMOLM2Prover 56 HF
DeepReasoning_1R 16 HF
SAGI 3 HF
S-AGI 0 HF

Top Models from Our Lab

Model Downloads
Qwen3-1.7B-Thinking-Distil 501
LFM2.5-1.2B-Distilled-SFT 342
Qwen3-1.7B-Coder-Distilled-SFT 302
Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF 203
Qwen3-1.7B-Coder-Distilled-SFT-GGUF 194

Total Portfolio: 41 models | 2,781 total downloads

Last updated: 2026-03-28 12:55 UTC

From the Convergent Intelligence Portfolio

DistilQwen Collection — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The rest of the portfolio proves structure beats scale on CPU. This collection shows what happens when you give the methodology real hardware.

Top model: Qwen3-1.7B-Coder-Distilled-SFT — 508 downloads

Full methodology: Structure Over Scale (DOI: 10.57967/hf/8165)

Convergent Intelligence LLC: Research Division

Part of the reaperdoesntknow research portfolio — 48 models, 12,094 total downloads | Last refreshed: 2026-03-29 21:05 UTC

Identity and Version

Repository
reaperdoesntknow/SMOLM2Prover-GGUF
Publisher
Convergent Intelligence
Task
Text generation
Modality
Text
Library
transformers
Parameters
Not stated by the source
Languages
en
Revision
b44095c04c83eaef84286dd90ee8faed1d4fefa7
First published
2026-03-08
Last updated
2026-09-18

Files and Weights

4 files, 996.2 MB in total. The weights are 2 files totalling 996.1 MB in gguf.

Weights2 files · 996.1 MB
Documentation1 file · 5.7 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
SMOLM2Prover-Q4_K_M.ggufWeights270.6 MB 55f1d76afef3
SMOLM2Prover.ggufWeights725.6 MB d350a1f1c1ce
README.mdDocumentation5.7 KB —
.gitattributesRepository1.6 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
996.1 MB
Download from Convergent Intelligence

Released by Convergent Intelligence through its official repository on Hugging Face. Read the license.

Built From

  • Derived from prithivMLmods/SmolLM2-CoT-360M
  • Quantized from prithivMLmods/SmolLM2-CoT-360M
  • Trained on (disclosed) AI-MO/NuminaMath-1.5

Memory Requirements

PrecisionWeights in memory
As published996.1 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About SMOLM2Prover-GGUF

Can I use SMOLM2Prover-GGUF commercially?

Yes. SMOLM2Prover-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Fine-tune Qwen3 (14B) for free using our Google Colab notebook! - Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3 - View the rest of our notebooks in our docs here. Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: - Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks. - Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding. - Agentic Coding supporting for…

Open weights apache-2.0 transformers
View model

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers
View model

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers
View model

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers
View model

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers
View model

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp
View model