SAVRN
Search Contact SAVRN

Open-weight model · Text generation

Qwen3.5-2B-Opus-Distil

by Convergent Intelligence reaperdoesntknow/Qwen3.5-2B-Opus-Distil

A 2B-parameter Qwen3.5 fine-tune, part of the Opus-Distil line in the reaperdoesntknow open-weight portfolio. Text-generation / reasoning model, trained with Unsloth + Hugging Face TRL.

Parameters2.3B
Context262,144
Weights4.6 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads4.2k

Runs On

What it takes to serve Qwen3.5-2B-Opus-Distil (2.3B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 4.5 GB 5.5 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 2.3 GB 2.7 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.1 GB 1.4 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

By Convergent Intelligence, published under apache-2.0, revision 859611936240.

A 2B-parameter Qwen3.5 fine-tune, part of the Opus-Distil line in the reaperdoesntknow open-weight portfolio. Text-generation / reasoning model, trained with Unsloth + Hugging Face TRL.

Read Convergent Intelligence's full model card

A 2B-parameter Qwen3.5 fine-tune, part of the Opus-Distil line in the reaperdoesntknow open-weight portfolio. Text-generation / reasoning model, trained with Unsloth + Hugging Face TRL.

Convergent Intelligence LLC: Research Division

  • Base model: unsloth/Qwen3.5-2B
  • License: Apache-2.0
  • Task: text-generation

Experimental research checkpoint. Not yet benchmarked — validate outputs before relying on them.

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("reaperdoesntknow/Qwen3.5-2B-Opus-Distil")
model = AutoModelForCausalLM.from_pretrained("reaperdoesntknow/Qwen3.5-2B-Opus-Distil", torch_dtype="auto", device_map="auto")

Configuration

Architecture
Qwen3_5ForConditionalGeneration
Context length (tokens)
262,144
Layers
24
Hidden size
2,048
Feed-forward size
6,144
Attention heads
8
Key/value heads
2
Head dimension
256
Vocabulary size
248,320
Stored precision
bfloat16
Model type
qwen3_5

Identity and Version

Repository
reaperdoesntknow/Qwen3.5-2B-Opus-Distil
Publisher
Convergent Intelligence
Task
Text generation
Modality
Text
Library
transformers
Parameters
2.3B parameters
Languages
en
Revision
8596119362402b5f9a837279dab90adf3dbbc57a
First published
2026-07-01
Last updated
2026-09-18

Files and Weights

12 files, 4.7 GB in total. The weights are 2 files totalling 4.6 GB in safetensors.

Weights2 files · 4.6 GB
Configuration5 files · 70.5 KB
Tokenizer2 files · 20.0 MB
Documentation1 file · 1.2 KB
Other1 file · 8.0 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
adapter_model.safetensorsWeights87.3 MB b4b2b8f5491a
model.safetensors-00001-of-00001.safetensorsWeights4.5 GB 3c4071d6b0e6
adapter_config.jsonConfiguration1.4 KB —
config.jsonConfiguration3.2 KB —
generation_config.jsonConfiguration141 B —
model.safetensors.index.jsonConfiguration64.5 KB —
processor_config.jsonConfiguration1.3 KB —
README.mdDocumentation1.2 KB —
chat_template.jinjaOther8.0 KB —
.gitattributesRepository1.6 KB —
tokenizer.jsonTokenizer20.0 MB 87a7830d63fc
tokenizer_config.jsonTokenizer7.2 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
4.6 GB
Download from Convergent Intelligence

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

Built From

  • Derived from unsloth/Qwen3.5-2B

Memory Requirements

PrecisionWeights in memory
As published4.6 GB
16-bit4.5 GB
8-bit2.3 GB
4-bit1.1 GB

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

Questions About Qwen3.5-2B-Opus-Distil

How much GPU memory does Qwen3.5-2B-Opus-Distil need?

About 5.5 GB at 16-bit and 1.4 GB at 4-bit: the weights (2.3B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run Qwen3.5-2B-Opus-Distil on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use Qwen3.5-2B-Opus-Distil commercially?

Yes. Qwen3.5-2B-Opus-Distil 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.

What is Qwen3.5-2B-Opus-Distil's context length?

262,144 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Text generation

Qwen3.5-2B-CyberSec

Convergent Intelligence

An English Qwen3.5 2B checkpoint associated with the Trendyol Cybersecurity Instruction Tuning Dataset and exported in Transformers / Safetensors format. This release is intended for research and local experimentation. The repository does not currently publish benchmark or safety-evaluation results, so the model should not be treated as a validated cybersecurity authority. The configuration identifies a Qwen3.5 conditional-generation architecture with text and vision components. Use a recent Transformers release that supports this architecture. Dependency and device behavior can vary across Transformers versions. Pin a tested environment for reproducible use. - Research on small-model…

Open weights apache-2.0 2.3B parameters 262,144 tokens transformers
View model

Model · Text generation

knivesysl-typed-2b

SRSWTI Inc.

local, typed decisions from qwen3.5-2b. one shared state is prefetched once, each question is isolated, every allowed answer is scored as a complete token sequence, and python returns validated choice, score, and noul results. this is an inference system, not rlcd training and not a clone of typesafe jev. it never calls typesafe. the published qwen checkpoint is unchanged; fp8 changes execution precision only. probabilities are normalized support over the candidates you provide, not calibrated correctness probabilities. unlike ordinary autoregressive json generation, the model does not write a response token by token. it scores only the values supplied by the caller. complete-sequence…

Open weights apache-2.0 2.3B parameters 262,144 tokens transformers
View model

Model · Text generation

Kimi-K3-DSpark

RadixArk

A long-context DSpark speculator for Kimi K3. It supports context lengths of up to 1 million tokens. A DSpark speculator for the Kimi K3 target, enabling faster inference through speculative decoding. DSpark extends the DFlash parallel-draft backbone with a Markov logit-bias head and a per-position confidence head. This checkpoint was trained with SpecForge using hidden states from a live SGLang target engine. 64 query heads / 16 KV heads, and blocksize=7 acclen is SGLang's histogram-native request acceptance length, averaged within each question and then equally across questions. RULER V2 uses the 1M input configuration. Actual prompts span 1,000,432–1,047,925 tokens; partition acclen is…

Open weights 2.2B parameters 1,048,576 tokens transformers
View model

Model · Text generation

Qwen3-1.7B

Qwen

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…

Open weights apache-2.0 2B parameters 40,960 tokens transformers
View model

Model · Text generation

TopologicalQwen

Convergent Intelligence

Topology-Aware Knowledge Distillation from Qwen3-30B-A3B → 1.7B TopologicalQwen is a 1.7B parameter model distilled from Qwen3-30B-A3B using Topological Knowledge Distillation (TKD) — a methodology that treats the teacher's output distribution over a concatenated token stream as a bounded variation (BV) function and decomposes knowledge transfer into three channels via the Mesh Fundamental Identity: 1. Smooth distillation (AC component) — Standard KL divergence over regions where the teacher's distribution varies continuously. This is what every other KD method does and stops at. 2. Jump corrections (D^j f) — Explicit correction terms at conceptual boundaries where the teacher's…

Open weights apache-2.0 2B parameters 40,960 tokens transformers
View model

Extended Reasoning Distillation from Qwen3-30B-A3B-Thinking → 1.7B The most downloaded model in the Convergent Intelligence portfolio. Qwen3-1.7B-Thinking-Distil captures extended deliberation patterns from the Qwen3-30B-A3B Thinking teacher — the variant that generates long-form reasoning chains before committing to an answer — and compresses them into a 1.7B student via supervised fine-tuning on the longwriter-6k dataset. The Thinking teacher produces the richest signal of the three teacher variants in the DistilQwen family (Instruct, Thinking, Coder). Where Instruct distillation captures clean instruction-following and Coder captures hierarchical decomposition, Thinking distillation…

Open weights apache-2.0 2B parameters 40,960 tokens transformers
View model