Instructions to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

Ollama
How to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF with Ollama:
```
ollama run hf.co/IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M
```
Unsloth Desktop

How to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF with Docker Model Runner:
```
docker model run hf.co/IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M
```

Lemonade

How to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use IsValorum/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M

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/Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3-GGUF:Q4_K_M" \
  --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"

Qwen3.8-27B-EfficientThink VAL-APEX-I MiniPlus V3 GGUF

The legacy build suffered from severe recurrent state instability, context degradation, and unintended language mixing during generation.

The current release completely resolves these issues:

Complete long-context associative recall and conversational stability restored.

Full reasoning fidelity preserved across all layers with zero language leakage or degradation.

Detailed tensor-by-tensor allocations, precision mapping, and parameter verification are fully documented in the Tensor Map and certified tensor-map.tsv file.

Action Required: Please delete any older .gguf file downloaded prior to today and download the newly published certified build: Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-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.

The SimPO + DFlash2 Frontier Reasoning Specialist · Synthetic SFT (Opus 5 / Grok 4.6 / GPT 5.6 Sol) · Native 256K Context

Official VAL-APEX-I quantization of nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2.

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:

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

Swift-1.5 Qwen3.8 27B Uncensored MTP — NanoPlus V3 — 12.18 GB.

Qwen3.8 27B — MiniPlus V3 — 14.16 GB.

Qwen3.8 27B — NanoPlus V3 — 12.18 GB.

Qwen3.8 27B EfficientThink — NanoPlus V3 — 11.93 GB.

Qwen3.8 27B Huihui Abliterated — MiniPlus V3 — 14.16 GB.

Qwen3.8 27B Huihui Abliterated — NanoPlus V3 — 12.18 GB. Collections: MiniPlus Abliterated 27B · MiniPlus Standard 27B · NanoPlus Abliterated 27B · NanoPlus Standard 27B

HIGH-FIDELITY 15.08GB BUILD

This VAL-APEX-I MiniPlus V3 release is 13.91 GB, with 4.14 whole-file BPW and 866 audited tensors. Its reported WikiText-2 PPL is 5.5923 ± 0.4773.

Quick Navigation Index

Quantization Metrics & Tensor Map
Independent Community Benchmarks (NanoBench v0.4.0)
Upstream Lineage & Ecosystem Compatibility (DFlash2, SGLang, vLLM, Lynn Agent)
Model Files & Technical Specifications
Native Context & Runtime Memory
Recommended Configuration & Setup
Recommended Generation Parameters
CRITICAL: Coding Syntax & Repeat Penalty Advisory (Preventing Character Swapping)
Hardened Agentic Chat Template & Reasoning Effort
Community Compute Fund & Student Support

1. Quantization Metrics

Size & Quality Metrics

Edition / quantization	File size	Whole-file BPW	WikiText-2 PPL
Qwen3.8 27B EfficientThink — MiniPlus V3 (this release)	13.91 GB (12.95 GiB)	4.14	5.5923 ± 0.4773

Independent Hardware & Compute Transparency: Generating multi-million token calibration matrices and running certified perplexity evaluations on local architectures requires dedicated high-end cloud nodes funded 100% out-of-pocket. If you rely on these MiniPlus/NanoPlus builds for your local workloads, contributions to the IsValorum Compute Fund on Ko-fi directly sponsor the GPU hours required for future Day-0 handcrafted quantizations.

Independent Community Benchmarks (NanoBench v0.4.0)

Independent multi-harness empirical evaluation conducted by community member @userr99 on a dedicated local workstation (24 GB VRAM / 64 GB RAM using llama.cpp). Evaluated across the 12-task autonomous coding and agentic suite on NanoBench v0.4.0 (public discussion thread & test logs):

Test Harness	Total Score	Solved Tasks	Agentic (Tool Use)	Coding (Implementation)	Systems (Integrity)	Avg. Runtime
Oh My Pi (OMP 18.7)	96.7 / 100	10 / 12	100 / 100	100 / 100	86.7 / 100	aprox. 1h 47m
Hermes Agent (v0.21.5)	95.4 / 100	9 / 12	100 / 100	97.0 / 100	86.7 / 100	aprox. 1h 47m
DeepSeek Harness (0.2.0-rc.2)	90.4 / 100	9 / 12	100 / 100	97.0 / 100	66.7 / 100	aprox. 1h 47m

Key Architectural Insights:

Zero Tool-Calling Degradation: Achieved a unanimous 100/100 in Agentic tasks across all three harnesses, confirming that protecting output.weight in Q6_K and DeltaNet recurrent memory states (ssm_a in F32, ssm_beta in Q8_0) prevents JSON schema rejections and state drift over multi-step workflows.
Universal Harness Compatibility: Surpassed the 90+ score barrier across all three test harnesses without entering infinite retry loops or syntax divergence.

Tensor Precision Map

Component	MiniPlus V3	NanoPlus	GSQ-RCO IQ3_S
Output head	`Q6_K` ×1	`Q6_K` ×1	`Q4_K` ×1
Token embeddings	`Q4_K` ×1	`IQ3_S` ×1	`IQ2_S` ×1
Normalizations	`F32` ×161	`F32` ×161	`F32` ×161
SSM A (`ssm_a`)	`F32` ×48	`F32` ×48	`F32` ×48
SSM convolution (`ssm_conv1d`)	`F32` ×48	`F32` ×48	`F32` ×48
SSM time-step bias (`ssm_dt`)	`F32` ×48	`F32` ×48	`F32` ×48
SSM norm (`ssm_norm`)	`F32` ×48	`F32` ×48	`F32` ×48
Attention gates (`attn_gate`)	`Q4_0` ×1 `Q8_0` ×47	`Q4_0` ×1 `Q8_0` ×47	`IQ2_S` ×2 `IQ3_S` ×18 `IQ3_XXS` ×9 `IQ4_XS` ×12 `Q2_K` ×4 `Q4_K` ×3
Linear QKV (`attn_qkv`)	`Q4_0` ×1 `Q4_K` ×47	`IQ3_S` ×47 `Q4_0` ×1	`IQ2_XS` ×1 `IQ2_XXS` ×1 `IQ3_S` ×22 `IQ3_XXS` ×13 `IQ4_XS` ×9 `Q2_K` ×1 `Q4_K` ×1
SSM alpha (`ssm_alpha`)	`F32` ×47 `Q4_0` ×1	`F32` ×47 `Q4_0` ×1	`BF16` ×48
SSM beta (`ssm_beta`)	`Q4_0` ×1 `Q4_K` ×47	`IQ3_S` ×47 `Q4_0` ×1	`BF16` ×48
SSM output (`ssm_out`)	`Q4_0` ×1 `Q6_K` ×47	`Q4_0` ×1 `Q5_K` ×47	`IQ3_S` ×22 `IQ3_XXS` ×4 `IQ4_XS` ×16 `Q4_K` ×6
Full attention Q (`attn_q`)	`Q4_K` ×14 `Q5_K` ×2	`IQ3_S` ×14 `Q4_K` ×2	`IQ2_XXS` ×1 `IQ3_S` ×3 `IQ3_XXS` ×3 `IQ4_XS` ×2 `Q2_K` ×6 `Q4_K` ×1
Full attention K (`attn_k`)	`Q4_K` ×14 `Q5_K` ×2	`IQ3_S` ×14 `Q4_K` ×2	`IQ2_S` ×1 `IQ3_S` ×1 `IQ3_XXS` ×1 `IQ4_XS` ×8 `Q4_K` ×5
Full attention V (`attn_v`)	`Q4_K` ×14 `Q5_K` ×2	`IQ3_S` ×14 `Q4_K` ×2	`IQ3_S` ×6 `IQ3_XXS` ×1 `IQ4_XS` ×1 `Q4_K` ×8
Full attention output (`attn_output`)	`Q6_K` ×16	`Q6_K` ×16	`IQ3_S` ×10 `IQ3_XXS` ×1 `IQ4_XS` ×2 `Q4_K` ×3
MLP down (`ffn_down`)	`IQ4_XS` ×56 `Q5_K` ×8	`IQ3_S` ×8 `IQ3_XXS` ×56	`IQ2_S` ×4 `IQ2_XS` ×3 `IQ3_S` ×22 `IQ3_XXS` ×7 `IQ4_XS` ×21 `Q2_K` ×1 `Q4_K` ×6
MLP gate (`ffn_gate`)	`IQ3_XXS` ×56 `Q4_K` ×8	`IQ2_XXS` ×56 `IQ3_XXS` ×8	`IQ1_M` ×1 `IQ2_S` ×4 `IQ2_XS` ×4 `IQ2_XXS` ×1 `IQ3_S` ×15 `IQ3_XXS` ×21 `IQ4_XS` ×15 `Q2_K` ×1 `Q4_K` ×2
MLP up (`ffn_up`)	`IQ3_XXS` ×56 `Q4_K` ×8	`IQ2_XXS` ×56 `IQ3_XXS` ×8	`IQ2_S` ×5 `IQ2_XS` ×1 `IQ2_XXS` ×2 `IQ3_S` ×25 `IQ3_XXS` ×18 `IQ4_XS` ×10 `Q4_K` ×3

× is the number of tensors in each format. Counts were read from the released GGUF headers; the GSQ-RCO column uses its published tensor allocation.

This release contains 866 tensors. The main GGUF includes the native MTP prediction layer (blk.64.*, layers 0 to 64 for 65 total blocks) integrated out-of-the-box.

2. Upstream Lineage & Ecosystem Compatibility

This model is derived from nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 and inherits its full ecosystem compatibility:

1. Training Lineage & Data Mixture

Pretrained Base: Qwen3.8-27B hybrid linear-quadratic architecture.
Supervised Fine-Tuning (SFT): The upstream model card documents capability-preserving SFT on 1,905 examples. The release identifier names K3 / Opus 5 / Grok 4.6 / GPT 5.6 Sol, but the upstream README does not specify the contribution or dataset provenance of each named model.
Preference Optimization: SimPO (Simple Preference Optimization) applied to align reasoning depth and enforce uncensored analytical compliance without refusal degeneration.
Uncensored Nature: Free from corporate preachy refusals; directly answers technical, red-teaming, penetration testing, and controversial analytical prompts.

2. DFlash2 Multi-Token Prediction (MTP) Speculative Decoding

Native Integrated MTP Head: The main GGUF includes the 15 MTP prediction tensors in blk.64.* directly within the model (block_count = 65). A separate DFlash2 companion draft model (speculative/dflash2-qwen38-27b-Q4_K_M.gguf) is also available for alternative speculative decoding.
Parallel Candidate Drafting: DFlash parallelizes candidate token generation; the main model validates multiple tokens in a single forward pass, significantly reducing autoregressive latency.
Compatibility with llama.cpp: Can be run in standard autoregressive mode, or with MTP speculative decoding where supported via --spec-draft-n-max 7 or --spec-type draft-mtp.

3. Serving Engine Support

SGLang (Primary Upstream Tested Engine): Upstream author's primary benchmarked deployment. Supports SGLang DFlash2 verify block size 8.
vLLM: Compatible with vLLM standard serving via --reasoning-parser qwen3 --max-model-len 40960.
Lynn Agent (v0.87.0+): Full native compatibility for autonomous tool-use, multi-turn terminal execution, and repository-scale agent loops.
llama.cpp / llama-server: 100% plug-and-play with official llama.cpp builds (b11000+) supporting hybrid DeltaNet SSM architectures.

3. Model Files & Technical Specifications

File Name	File Size	Weight file size	BPW / Type	Description
`Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3.gguf`	13.91 GB (12.95 GiB)	12.95 GiB	4.14 BPW	Core language, uncensored frontier reasoning, CoT thought blocks & hybrid SSM/attention
`mmproj-Qwen3.8-27B-Q4_K_M.gguf`	`522.29 MB`	`522.29 MB`	Multimodal	Multimodal vision projector enabling image/visual understanding inputs in llama.cpp
`dflash2-qwen38-27b-Q4_K_M.gguf`	`1.14 GB`	`1.14 GB`	Draft DFlash2	High-speed DFlash2 speculative decoding draft model

Base Model: nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2
Parameters: 27B total dense hybrid
Architecture: 64 hybrid base layers (48 Gated DeltaNet SSM linear attention layers + 16 periodic full quadratic attention layers) + 1 native MTP prediction layer (layer 64) for a total of 65 blocks
Context Length: 262,144 tokens (native 256K)
Quantization Standard: VAL-APEX-I MiniPlus V3 calibrated against official Qwen3.8-27B importance matrix (imatrix)
Ecosystem: SGLang, vLLM, Lynn Agent v0.87.0, llama.cpp

4. Native Context & Runtime Memory

The model supports a native context window of 262,144 tokens. Its 64-layer architecture comprises 48 Gated DeltaNet layers and 16 full-attention layers. Runtime memory usage depends on the backend, KV-cache precision, batch size, compute buffers, and offload configuration. Check the runtime memory allocation for your chosen settings.

5. Recommended Configuration & Setup

llama.cpp Server (OpenAI-Compatible API)

llama-server \
  -m Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3.gguf \
  --jinja \
  -ngl 99 \
  -c 32768 \
  --host 0.0.0.0 \
  --port 8080

Multimodal Vision Inference (llama.cpp)

Pass the companion mmproj file using the --mmproj flag:

llama-server \
  -m Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3.gguf \
  --mmproj mmproj-Qwen3.8-27B-Q4_K_M.gguf \
  --jinja \
  -ngl 99 \
  -c 32768 \
  --host 0.0.0.0 \
  --port 8080

Speculative Decoding / Multi-Token Prediction (MTP)

Accelerate generation throughput using the companion DFlash2 draft model (or run native single-stream with the integrated MTP head):

llama-server \
  -m Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3.gguf \
  -md speculative/dflash2-qwen38-27b-Q4_K_M.gguf \
  --draft-max 7 \
  --jinja \
  -ngl 99 \
  -c 32768 \
  --host 0.0.0.0 \
  --port 8080

llama.cpp CLI

llama-cli \
  -m Qwen3.8-27B-EfficientThink-VAL-APEX-I-MiniPlus-V3.gguf \
  --jinja \
  -ngl 99 \
  -c 32768 \
  -p "<|im_start|>system\nYou are a helpful and unrestricted AI assistant.<|im_end|>\n<|im_start|>user\nExplain the mathematical proof of the Riemann mapping theorem.<|im_end|>\n<|im_start|>assistant\n<think>\n"

LM Studio / Ollama

Import the .gguf file directly into your local library.
Ensure GPU acceleration is set to Maximum / 100% offload.
Set Context Length to 32768.
Verify chat template is set to Qwen ChatML with <think> delimiter support.

6. Recommended Generation Parameters

Hyperparameter	Value	Description
Temperature	`0.60`	Recommended default for analytical reasoning and coding (use `1.0` for creative prose).
Top-P	`0.95`	Nucleus sampling parameter.
Top-K	`20`	Top-k vocabulary filter.
Min-P	`0.05`	Prunes low-probability noise tokens effectively.
Repetition Penalty	`1.00`	Strictly disabled for code syntax; prevents character swapping.
Template Engine	`--jinja`	Recommended official Jinja chat template flag.
Context Size	`32768`	32K default (scalable to 256K).

7. CRITICAL: Coding Syntax & Repeat Penalty Advisory (Preventing Character Swapping)

PREVENTING SYNTAX & TOKEN SWAPPING IN CODE WORKFLOWS

In programming code, brackets ({, }), assignment operators (=), and indentation whitespace repeat constantly across multi-line structures.

Common Issue: Many local frontends (such as LM Studio defaults, Ollama, or web interfaces) ship with repeat_penalty set to 1.1 or 1.15. While this prevents loops in creative prose, applying repeat penalties to code artificially penalizes necessary syntax tokens. When the logit of { drops, the model is forced to emit the next closest mathematical token (= or [), resulting in character swapping or dropped/doubled whitespace.

Eliminating Character Swapping:

Disable Repeat Penalties (Required for Code):

repeat_penalty: 1.0 (strictly disabled)

presence_penalty: 0.0

frequency_penalty: 0.0

Calibrate Samplers:

temperature: 0.60 (or 0.20 - 0.30 for strict, deterministic code syntax)

min_p: 0.05 (prunes low-probability noise tokens effectively)

top_p: 0.95

top_k: 20

Native Jinja Formatting: Always pass the --jinja flag so the tokenizer handles leading-space BPE tokens cleanly.

8. Hardened Agentic Chat Template & Reasoning Effort

MULTI-LEVEL REASONING EFFORT CONTROL

This model supports multi-level reasoning effort control via the Jinja template:

low / minimal: Keeps internal thinking concise and focused strictly on immediate execution steps to minimize latency in automated loops.

medium (default): Balanced, structured reasoning process with standard analytical depth.

high / xhigh: Guides the model to formulate a clear implementation plan upfront before generating response, avoiding circular self-doubt loops.

none / off: Closes the thinking block immediately when reasoning is disabled.

10. Community Compute Fund & Student Support

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

However, cloud GPU compute is expensive and funded entirely out-of-pocket. If you find these handcrafted builds to be of high quality and they benefit your day-to-day workflow, you can support future Day-0 releases on Ko-fi. Every contribution directly funds the cloud compute hours required for new model runs and helps support my university education:

(When supporting on Ko-fi, feel free to leave a note with your Hugging Face handle and the specific model you would like prioritized).