# Model Research: Small LMs for LoRA/QLoRA Fine-Tuning

> **Date:** 2026-03-18
> **Purpose:** Evaluate small language models (4-14B) as base models for the Minecraft server ops assistant.
> **Constraints:**
> - 8GB VRAM for inference (Q4 quantized via Ollama)
> - 24GB VRAM for training (QLoRA)
> - Permissive license (Apache 2.0, MIT -- NOT community/restricted licenses)
> - Available on both Ollama (serving) and HuggingFace in safetensors/PyTorch (training)
> - Good instruction following and structured JSON output
> - Active fine-tuning ecosystem (Unsloth, Axolotl, PEFT, LlamaFactory)

---

## Ranked Recommendations

### 1. Qwen3-8B (RECOMMENDED)

| Attribute | Detail |
|-----------|--------|
| **Parameters** | 8B dense |
| **Release** | April 2025 |
| **License** | Apache 2.0 |
| **HuggingFace** | `Qwen/Qwen3-8B` -- safetensors, BF16 |
| **Ollama** | `ollama pull qwen3:8b` |
| **Q4 VRAM** | ~5.5 GB (fits 8GB comfortably) |
| **QLoRA VRAM** | ~14-16 GB (fits 24GB easily) |
| **Context** | 128K native |

**Why #1:**
- Outperforms Qwen2.5-14B on benchmarks despite being smaller. MMLU-Redux ~87, MATH-500 ~98.
- Apache 2.0 with no usage restrictions -- the cleanest license in this list.
- First-class Unsloth support with dedicated notebooks and 2x training speedup.
- Supported by Axolotl, LlamaFactory, PEFT, and TRL out of the box.
- Native thinking/non-thinking mode toggle -- useful for complex command generation vs. quick lookups.
- Strong structured output support; JSON format instructions work reliably.
- Massive community: most fine-tuned derivatives on HuggingFace of any model this size.

**Caveats:**
- Newer than some alternatives, so fewer battle-tested fine-tunes in production.

---

### 2. Qwen3.5-4B

| Attribute | Detail |
|-----------|--------|
| **Parameters** | 4B dense |
| **Release** | February 2026 |
| **License** | Apache 2.0 |
| **HuggingFace** | `Qwen/Qwen3.5-4B` -- safetensors, BF16/F32 |
| **Ollama** | `ollama pull qwen3.5:4b` (~3.4 GB) |
| **Q4 VRAM** | ~2.5-3 GB |
| **QLoRA VRAM** | ~8-10 GB |
| **Context** | 256K native |

**Why #2:**
- The newest model on this list (Feb 2026) with latest training techniques.
- Extremely lightweight -- leaves massive headroom for context on 8GB cards.
- 256K context window is best-in-class for this parameter range.
- Full Unsloth + LlamaFactory support confirmed.
- Apache 2.0 license, no restrictions.
- Ideal if your training data is small (<1000 examples) -- smaller models fine-tune faster and can still match larger models on narrow domains.

**Caveats:**
- 4B may struggle with complex multi-step reasoning compared to 8B.
- Fewer community fine-tunes available yet (very new release).

---

### 3. Qwen3-4B

| Attribute | Detail |
|-----------|--------|
| **Parameters** | 4B dense (36-layer transformer) |
| **Release** | April 2025 |
| **License** | Apache 2.0 |
| **HuggingFace** | `Qwen/Qwen3-4B` -- safetensors |
| **Ollama** | `ollama pull qwen3:4b` |
| **Q4 VRAM** | ~2.5 GB |
| **QLoRA VRAM** | ~8-10 GB |
| **Context** | 128K native |

**Why #3:**
- Benchmarks rival Qwen2.5-72B-Instruct (!!) according to Qwen team claims.
- MMLU-Redux 83.7, MATH-500 97.0 -- exceptional for 4B.
- Well-established Unsloth support with notebooks and GGUF export pipeline.
- Best fine-tuning benchmark results per distillabs.ai evaluation: "Qwen3-4B-Instruct-2507 delivers the best overall fine-tuned performance, matching a 120B+ teacher."
- Apache 2.0.

**Caveats:**
- Slightly older than Qwen3.5-4B; same parameter count but older architecture.

---

### 4. Phi-4-mini-instruct (3.8B)

| Attribute | Detail |
|-----------|--------|
| **Parameters** | 3.8B |
| **Release** | February 2025 |
| **License** | MIT |
| **HuggingFace** | `microsoft/Phi-4-mini-instruct` -- safetensors |
| **Ollama** | `ollama pull phi4-mini:3.8b` |
| **Q4 VRAM** | ~2.5 GB |
| **QLoRA VRAM** | ~8-10 GB |
| **Context** | 128K |

**Why #4:**
- MIT license -- the most permissive option available.
- Microsoft provides an official LoRA fine-tuning script in the HuggingFace repo.
- Performance comparable to 7-9B models (Llama-3.1-8B level) despite being 3.8B.
- 200K vocabulary, grouped-query attention -- modern architecture.
- JSON tool-calling format built into the chat template.
- Unsloth support confirmed with dedicated notebooks.

**Caveats:**
- Smaller community of fine-tuners compared to Qwen.
- 3.8B is the smallest viable option; may need more training data to match larger models on nuanced tasks.
- Microsoft's Phi models have historically had some quirks with non-English content and repetition.

---

### 5. Gemma 3 4B-IT

| Attribute | Detail |
|-----------|--------|
| **Parameters** | 4B (multimodal -- text + image) |
| **Release** | March 2025 |
| **License** | Gemma Terms of Use (NOT Apache 2.0 -- see caveats) |
| **HuggingFace** | `google/gemma-3-4b-it` -- safetensors |
| **Ollama** | `ollama pull gemma3:4b` (~3.3 GB) |
| **Q4 VRAM** | ~2.5 GB |
| **QLoRA VRAM** | ~8-10 GB |
| **Context** | 128K |

**Why #5:**
- Outperforms Gemma 2 27B on benchmarks -- a 7x smaller model beating its predecessor's flagship.
- Google provides official LoRA fine-tuning docs with Keras and HuggingFace PEFT.
- QAT (Quantization-Aware Training) variants available for better quantized performance.
- Native function calling and structured output support.
- Multimodal capability (text + images) could be useful for screenshot-based troubleshooting.
- Unsloth, Axolotl, and LlamaFactory all support Gemma 3.

**Caveats:**
- **License is NOT Apache 2.0.** Gemma Terms of Use allow commercial use but include a Prohibited Use Policy covering sensitive domains. Google retains the right to "restrict (remotely or otherwise) usage." This is more restrictive than Apache 2.0/MIT.
- For a personal Minecraft server project this is likely fine, but it fails the strict "permissive license" requirement.

---

### 6. Gemma 3 12B-IT

| Attribute | Detail |
|-----------|--------|
| **Parameters** | 12B (multimodal) |
| **Release** | March 2025 |
| **License** | Gemma Terms of Use (same caveats as 4B) |
| **HuggingFace** | `google/gemma-3-12b-it` -- safetensors |
| **Ollama** | `ollama pull gemma3:12b` |
| **Q4 VRAM** | ~6.6 GB (Google claims RTX 4060 8GB works) |
| **QLoRA VRAM** | ~18-20 GB (fits 24GB) |
| **Context** | 128K |

**Why #6:**
- The largest model that can fit in 8GB VRAM at Q4.
- Best raw capability of any model on this list.
- QAT Q4 variants from Google specifically optimized for consumer GPUs.
- Full Unsloth support.

**Caveats:**
- Tight fit on 8GB -- leaves little headroom for KV cache with long prompts.
- Same license concerns as Gemma 3 4B.
- QLoRA training at 12B needs more VRAM; will use ~18-20 GB of your 24GB budget.

---

### 7. Mistral NeMo 12B

| Attribute | Detail |
|-----------|--------|
| **Parameters** | 12B |
| **Release** | July 2024 |
| **License** | Apache 2.0 |
| **HuggingFace** | `mistralai/Mistral-Nemo-Instruct-2407` -- safetensors |
| **Ollama** | `ollama pull mistral-nemo:12b` |
| **Q4 VRAM** | ~7 GB |
| **QLoRA VRAM** | ~18-22 GB (higher due to large vocabulary) |
| **Context** | 128K |

**Why #7:**
- Apache 2.0 license, built with NVIDIA collaboration.
- 128K context, strong multilingual support.
- Established fine-tuning ecosystem with mistral-finetune tool.

**Caveats:**
- Oldest model on this list (July 2024) -- outperformed by newer 4-8B models on many benchmarks.
- Large vocabulary (32K+ tokens) increases memory requirements for fine-tuning beyond what the parameter count suggests.
- Tight fit on 8GB VRAM at Q4 with limited context headroom.
- Not recommended over Qwen3-8B which is newer, smaller, and benchmarks better.

---

## Models Considered and Rejected

| Model | Reason for Rejection |
|-------|---------------------|
| **Llama 3.2 (1B/3B)** | Llama Community License prohibits using outputs to train non-Llama models. Distillation restrictions. Not truly permissive. |
| **Llama 3.1-8B / 3.3-70B** | Same license restrictions as above. The 700M MAU clause and output training restrictions disqualify it. |
| **Qwen3-Coder (30B-A3B, 480B)** | All variants are massive MoE models. Even the smallest (30B-A3B with 3B active) has 30B total parameters -- too large for 8GB inference and questionable for 24GB QLoRA. |
| **Mistral Small 3 (24B)** | 24B parameters -- requires ~14 GB VRAM at Q4. Does not fit 8GB. |
| **Phi-4 (14B)** | Fits 8GB at Q4 (~8-9 GB) only marginally. QLoRA at 14B needs ~22-24 GB, cutting it very close. The 3.8B Phi-4-mini is a better fit for this project. |
| **Gemma 2 (9B/27B)** | Superseded by Gemma 3. No reason to use older generation. |
| **Qwen2.5 (7B/14B)** | Superseded by Qwen3 and Qwen3.5 with significantly better benchmarks. |

---

## Fine-Tuning Ecosystem Comparison (as of March 2026)

| Framework | Qwen3/3.5 | Phi-4-mini | Gemma 3 | Mistral NeMo |
|-----------|-----------|------------|---------|--------------|
| **Unsloth** | Full support, dedicated notebooks, 2x speedup | Supported, notebooks available | Supported, Gemma 3n confirmed | Supported |
| **Axolotl** | Supported | Supported | Supported | Supported |
| **LlamaFactory** | Supported, Ollama export | Supported | Supported | Supported |
| **HF PEFT/TRL** | Supported | Supported, official script | Supported, Google official docs | Supported |
| **Community notebooks** | Abundant | Moderate | Abundant | Moderate |

---

## Recommendation for This Project

**Primary: Qwen3-8B** -- Best balance of capability, VRAM fit, license cleanliness, and fine-tuning ecosystem. It significantly outperforms older 14B models while fitting comfortably in 8GB at Q4. Apache 2.0 means zero legal concerns.

**Secondary: Qwen3-4B or Qwen3.5-4B** -- If training data is limited (<500 examples) or you want faster iteration cycles, a 4B model will fine-tune faster and still perform well on the narrow domain of Minecraft server operations. Qwen3.5-4B is newer with a 256K context window; Qwen3-4B has more proven fine-tuning results.

**Note on qwen3-coder:** The current PLAN.md references `qwen3-coder` as the base model. All Qwen3-Coder variants are large MoE models (30B+ total parameters) that do not fit the 8GB inference constraint. The recommendation is to use **Qwen3-8B** (or Qwen3-4B) as the base model instead. The coding/command-generation capability can be developed through fine-tuning on domain-specific data rather than requiring a code-specialized base model.

---

## Sources

- [Qwen3 announcement and benchmarks](https://qwenlm.github.io/blog/qwen3/)
- [Qwen3.5 on HuggingFace](https://huggingface.co/Qwen/Qwen3.5-4B)
- [Qwen3.5 on Ollama](https://ollama.com/library/qwen3.5)
- [Phi-4-mini-instruct on HuggingFace](https://huggingface.co/microsoft/Phi-4-mini-instruct)
- [Phi-4-mini on Ollama](https://ollama.com/library/phi4-mini:3.8b)
- [Gemma 3 on Ollama](https://ollama.com/library/gemma3)
- [Gemma 3 QAT models for consumer GPUs](https://developers.googleblog.com/en/gemma-3-quantized-aware-trained-state-of-the-art-ai-to-consumer-gpus/)
- [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
- [Gemma license risk analysis](https://wcr.legal/google-gemma-license-risks/)
- [Mistral NeMo on HuggingFace](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)
- [Mistral NeMo on Ollama](https://ollama.com/library/mistral-nemo)
- [Unsloth model catalog](https://unsloth.ai/docs/get-started/unsloth-model-catalog)
- [Unsloth Qwen3 fine-tuning guide](https://unsloth.ai/docs/models/qwen3-how-to-run-and-fine-tune)
- [Unsloth Qwen3.5 fine-tuning guide](https://unsloth.ai/docs/models/qwen3.5/fine-tune)
- [Unsloth Phi-4 fine-tuning](https://unsloth.ai/blog/phi4)
- [Unsloth Gemma 3 fine-tuning](https://unsloth.ai/blog/gemma3)
- [Fine-tuning framework comparison 2026](https://dev.to/ultraduneai/eval-003-fine-tuning-in-2026-axolotl-vs-unsloth-vs-trl-vs-llama-factory-2ohg)
- [Distillabs SLM fine-tuning benchmark](https://www.distillabs.ai/blog/we-benchmarked-12-small-language-models-across-8-tasks-to-find-the-best-base-model-for-fine-tuning)
- [JSONSchemaBench structured output benchmark](https://arxiv.org/abs/2501.10868)
- [Llama license restrictions analysis](https://wcr.legal/llama-3-license-700m-mau-limit/)
- [Qwen3-Coder on HuggingFace](https://huggingface.co/collections/Qwen/qwen3-coder)
- [Top SLMs 2026 overview (DataCamp)](https://www.datacamp.com/blog/top-small-language-models)
- [Best open-source SLMs 2026 (BentoML)](https://www.bentoml.com/blog/the-best-open-source-small-language-models)