Instructions to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF 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 IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF: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 IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF: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 IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Use Docker

docker model run hf.co/IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Ollama
How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with Ollama:
```
ollama run hf.co/IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0
```
Unsloth Desktop

How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with Docker Model Runner:
```
docker model run hf.co/IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0
```

Lemonade

How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Run and chat with the model

lemonade run user.Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Swift-1.5-Qwen3.8-27B-Uncensored-MTP VAL-APEX-I NanoPlus V3 GGUF

Independently computed using dedicated cloud compute clusters, funded 100% out-of-pocket.

If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies.

Uncensored Frontier 27B Dense Hybrid Reasoning Model with Intact Vision, Multilingual Syntax Preservation, and Native MTP Self-Speculation

Official VAL-APEX-I NanoPlus V3 quantization of ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-MTP. This edition quantizes the uncensored foundation model built on UkisAI's Swift-1.5 reasoning fine-tune of Qwen3.8-27B with the official canonical V3 recipe (strictly enforcing IQ4_XS and protecting attention/recurrent matrices).

Multilingual Source Model: Preserves the source model's multilingual tokenizer and native chat template.
Native MTP Speculative Head Included: Features the built-in Multi-Token Prediction auxiliary head (blk.64.*, 15 tensors), for MTP speculative decoding in compatible backends without an external draft model.
Multimodal Optical Vision: Retains the high-precision vision encoder (mmproj-Q8_0.gguf) for visual and document reasoning.
ISTA-DASLab Calibrated: Quantized with the official ISTA-DASLab importance matrix (imatrix-qwen3.8-27b.gguf) computed across diverse tokens to safeguard critical recurrent and projection weights.

VAL-APEX-I stands for: Vector-calibrated Asymmetric Layer-wise Outlier-preserving Recurrent-aware Unified Matrix-quantization

EXPLORE THE QWEN3.8 27B VAL-APEX-I EDITIONS

Choose a model variant and quantization profile:

Qwen3.8 27B — MiniPlus V3 — 14.16 GB.

Qwen3.8 27B — NanoPlus V3 — 12.18 GB.

Swift-1.5 Qwen3.8 27B Uncensored MTP — MiniPlus V3 — 14.16 GB.

VAL-APEX-I collection · MiniPlus collection · NanoPlus collection

1. Quantization Metrics

Size & Quality Metrics

Edition / quantization	File size	Whole-file BPW	WikiText-2 PPL
Swift-1.5 Qwen3.8 27B Uncensored MTP NanoPlus V3 (this release)	12.18 GB (11.35 GiB)	3.57	6.2593

This NanoPlus edition was evaluated on WikiText-2 under the same conditions as its previous recipe, as confirmed by the release maintainer. Its reported PPL changed from 6.9102 to 6.2593 (9.42% lower). The current evaluation uses llama-perplexity with context 512, batch 512, four chunks and GPU offload (-ngl 99), from llama.cpp build 11512 (a11f57ba9).

Whole-file BPW is calculated from the complete GGUF file size and its 27,320,697,856 stored parameters, including MTP.

Evaluation runs: current canonical V3 job · previous recipe job.

Tensor Precision Map

Component	MiniPlus V3	NanoPlus V3	GSQ-RCO IQ3_S
Output head	`Q6_K` x1	`Q5_K` x1	`Q4_K` x1
Token embeddings	`Q4_K` x1	`Q3_K` x1	`IQ2_S` x1
Normalizations	`F32` x161	`F32` x161	`F32` x161
SSM A (`ssm_a`)	`F32` x48	`F32` x48	`F32` x48
SSM convolution (`ssm_conv1d`)	`F32` x48	`F32` x48	`F32` x48
SSM time-step bias (`ssm_dt`)	`F32` x48	`F32` x48	`F32` x48
SSM norm (`ssm_norm`)	`F32` x48	`F32` x48	`F32` x48
Attention gates (`attn_gate`)	`Q4_0` x1 `Q4_K` x47	`Q4_0` x1 `Q4_K` x47	`IQ2_S` x2 `IQ3_S` x18 `IQ3_XXS` x9 `IQ4_XS` x12 `Q2_K` x4 `Q4_K` x3
Linear QKV (`attn_qkv`)	`Q4_0` x1 `Q4_K` x47	`Q3_K` x47 `Q4_0` x1	`IQ2_XS` x1 `IQ2_XXS` x1 `IQ3_S` x22 `IQ3_XXS` x13 `IQ4_XS` x9 `Q2_K` x1 `Q4_K` x1
SSM alpha (`ssm_alpha`)	`F32` x48	`F32` x48	`BF16` x48
SSM beta (`ssm_beta`)	`Q4_0` x1 `Q8_0` x47	`Q4_0` x1 `Q8_0` x47	`BF16` x48
SSM output (`ssm_out`)	`Q4_0` x1 `Q5_K` x47	`Q4_0` x1 `Q4_K` x47	`IQ3_S` x22 `IQ3_XXS` x4 `IQ4_XS` x16 `Q4_K` x6
Full attention Q (`attn_q`)	`Q4_K` x16	`Q3_K` x16	`IQ2_XXS` x1 `IQ3_S` x3 `IQ3_XXS` x3 `IQ4_XS` x2 `Q2_K` x6 `Q4_K` x1
Full attention K (`attn_k`)	`Q5_K` x16	`Q4_K` x16	`IQ2_S` x1 `IQ3_S` x1 `IQ3_XXS` x1 `IQ4_XS` x8 `Q4_K` x5
Full attention V (`attn_v`)	`Q6_K` x16	`Q5_K` x16	`IQ3_S` x6 `IQ3_XXS` x1 `IQ4_XS` x1 `Q4_K` x8
Full attention output (`attn_output`)	`Q6_K` x16	`Q5_K` x16	`IQ3_S` x10 `IQ3_XXS` x1 `IQ4_XS` x2 `Q4_K` x3
MLP down (`ffn_down`)	`IQ4_XS` x64	`IQ3_XXS` x48 `IQ4_XS` x16	`IQ2_S` x4 `IQ2_XS` x3 `IQ3_S` x22 `IQ3_XXS` x7 `IQ4_XS` x21 `Q2_K` x1 `Q4_K` x6
MLP gate (`ffn_gate`)	`IQ3_S` x32 `IQ3_XXS` x32	`IQ3_XXS` x64	`IQ1_M` x1 `IQ2_S` x4 `IQ2_XS` x4 `IQ2_XXS` x1 `IQ3_S` x15 `IQ3_XXS` x21 `IQ4_XS` x15 `Q2_K` x1 `Q4_K` x2
MLP up (`ffn_up`)	`IQ3_S` x32 `IQ3_XXS` x32	`IQ3_XXS` x64	`IQ2_S` x5 `IQ2_XS` x1 `IQ2_XXS` x2 `IQ3_S` x25 `IQ3_XXS` x18 `IQ4_XS` x10 `Q4_K` x3
Additional MTP head (`blk.64.*`)	`F32` x7 `Q4_0` x6 `Q4_1` x1 `Q6_K` x1	`F32` x7 `Q4_0` x6 `Q4_1` x1 `Q5_K` x1	-

x denotes tensor counts. All columns reflect exact GGUF tensor headers verified in tensor-map.tsv. Normalizations exclude separately listed SSM norms.

Both Swift/Base/Huihui files contain 866 audited tensors: 851 main-model tensors plus 15 MTP tensors. The main model is a dense hybrid architecture with 64 layers: 48 Gated DeltaNet linear-attention layers and 16 full-attention layers. The additional blk.64.* block is the integrated MTP head.

V3 architectural allocation: NanoPlus V3 features an elevated 3-bit floor across all SwiGLU MLP blocks (ffn_gate and ffn_up set uniformly to IQ3_XXS across all 64 layers; ffn_down uses IQ4_XS in outer layers 0-7 / 56-63 and IQ3_XXS in core layers 8-55). Output head (output.weight) is calibrated to Q5_K (5.50 bpw) to maximize token throughput and preserve dynamic range, entirely eliminating the linguistic decay in non-English contexts associated with 2-bit sub-allocations.

Actual layer-0 formats: blk.0.attn_gate.weight, blk.0.attn_qkv.weight, blk.0.ssm_beta.weight and blk.0.ssm_out.weight use Q4_0. All 48 ssm_alpha tensors remain F32 for mathematical stability.

Integrated MTP: blk.64.* contains 424,699,392 stored parameters in 15 tensors: seven F32 tensors and eight matrices (Q4_0 x6, Q4_1 x1, Q5_K x1). Runtime acceleration depends on backend support and configuration; speculative decoding operates via native acceptance drafting.

Complete tensor-by-tensor audit: names, formats, shapes and parameter counts.

2. Model Files & Technical Specifications

File Name	File Size	Whole-file BPW	Description
`Swift-1.5-Qwen3.8-27B-Uncensored-VAL-APEX-I-NanoPlus-V3.gguf`	12.18 GB (11.35 GiB)	3.57 BPW	Primary NanoPlus V3 quantized model with integrated MTP head
`mmproj-Q8_0.gguf`	`629.25 MB` (`600.10 MiB`)	10.93 BPW	Q8_0 multimodal vision projector with F32 and F16 tensors

Architecture: qwen35, dense hybrid Gated DeltaNet / full attention.
Native context: 262,144 tokens (256K).
Stored parameters: 27,320,697,856, including 424,699,392 in the MTP head.
Vision projector: 334 tensors; Q8_0 ×83, F16 ×27 and F32 ×224. Its filename describes the quantization profile, not a uniform format for every tensor.

3. Recommended Configuration & Setup

llama-server (OpenAI-Compatible API with Native MTP Self-Speculation)

llama-server \
  -m Swift-1.5-Qwen3.8-27B-Uncensored-VAL-APEX-I-NanoPlus-V3.gguf \
  --mmproj mmproj-Q8_0.gguf \
  --port 8080 \
  --spec-type draft-mtp \
  --spec-draft-n-max 2 \
  -ngl 99 \
  -c 16384

4. Community Compute Fund & Priority Model Requests

All IsValorum quantizations will always remain completely free and open to the public without paywalls.

If you find these builds valuable and would like to support the project or sponsor GPU compute time, you can contribute via Ko-fi:

Downloads last month: 3,319

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF

Base model

Qwen/Qwen3.8-27B

Finetuned

ukisai/Swift-1.5-Qwen3.8-27b

Finetuned

ajgazin/Swift-1.5-Qwen3.8-27B-Uncensored-MTP

Quantized

(15)

this model

Spaces using IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF 2

Collection including IsValorum/Swift-1.5-Qwen3.8-27B-Uncensored-MTP-VAL-APEX-I-NanoPlus-V3-GGUF

VAL-APEX-I

Collection

Official collection of models quantized under the VAL-APEX-I standard for dense hybrid linear-quadratic architectures. • 8 items • Updated 4 days ago