This is an MLX-format conversion of iapp/ChindaMT-4B by iApp AI Research.
All credit for the model weights, training, and translation capability belongs to the original authors.
This repo only provides an Apple Silicon–compatible format. No retraining or modification of weights was done.
Converted to MLX + 4-bit quantization (group_size=32)
License
Apache-2.0 (same as original)
Converted by
veha — format conversion + quantization only
Uses group_size=32 for finer quantization granularity. 94.6% semantic fidelity — best balance of size and quality for casual use.
Quick Start
bash
1pip install mlx-lm
23mlx_lm.generate \4 --model veha/ChindaMT-4B-MLX-4bit \5 --prompt "Translate English to Thai.
67EN: The meeting has been postponed until next Friday."\8 --max-tokens 256 --temp 0
Python:
python
1from mlx_lm import load, generate
23model, tokenizer = load("veha/ChindaMT-4B-MLX-4bit")4response = generate(model, tokenizer,"Translate English to Thai.\n\nEN: The weather is nice today.", temp=0)5print(response)
Fidelity = cosine semantic similarity against original HuggingFace weights (multilingual sentence embeddings). 100/100 prompts identical for bf16, 81/100 for 8bit, 37/100 for 4bit.
Evaluation
Corrected 100-prompt evaluation, 50 EN->TH and 50 TH->EN pairs:
Evaluation script: eval/full_table.py. Metrics use multilingual sentence embeddings for semantic similarity, chrF++ with word_order=2, and character-level BLEU.
Conversion Method
This repo was built with MLX-LM 0.31.3 from the original Hugging Face model.
Download the original model after accepting access to iapp/ChindaMT-4B:
Note: --q-group-size 32 provides finer quantization granularity than the default 64.
Post-process the release folder:
Keep Apache-2.0 license metadata and add a LICENSE file.
Add .gitattributes so safetensors files are stored with Git LFS.
Remove the forced <think> generation prefix from chat_template.jinja; this is a translation model, so LM Studio and other clients should display translations as normal assistant output, not reasoning text.
Remove tool_parser_type: qwen3_coder from tokenizer_config.json; this model is released for translation, not tool calling.
Evaluate the quantized model against the original HF model and MLX bf16:
python eval/full_table.py
This Disclaimer, Translated by Every Variant
The disclaimer above, translated by each MLX variant. A real-world quality comparison on this very text:
This is a conversion of the MLX format for iapp/ChindaMT-4B by iApp AI Research. All credits for the model weights, training, and translation capabilities belong to the original creators. This repository provides only the Apple Silicon-compatible format. No retraining or modification of the model weights has been performed.
This is a conversion of the MLX format for iapp/ChindaMT-4B by iApp AI Research. All credits for the model weights, training, and translation capabilities belong to the original creators. This repository provides only the Apple Silicon-compatible format. No retraining or modification of the model weights has been performed.
4bit (this)
This is a conversion of the MLX format for iapp/ChindaMT-4B by iApp AI Research. All credits for the model weights, training, and translation capabilities belong to the original creators. This repository contains only formats compatible with Apple Silicon. No retraining or modification of the model weights has been performed.
Quantization Comparison: Real Examples
How much does quantization actually affect translation quality? Here are hand-picked examples where the variants diverge:
Example 1: Proper Nouns (EN→TH)
Input:Christoph Müller will present at the ASEAN Business Summit in Bangkok on December 15, 2025.
I can translate this Thai phrase into English. The phrase "ยอมแลกกับอะไรก็ได้" literally means "willing to exchange for anything." It expresses a stro…
I can translate this Thai phrase into English. The phrase "ยอมแลกกับอะไรก็ได้" literally means "willing to exchange for anything." It expresses a stro…
4bit (this)
TH: I will exchange it for anything.
Observation: FP/Q8 try to explain the Thai phrase instead of simply translating it. Q4 produces a more direct translation — arguably better, but inconsistent with FP behavior.
Example 3: Tone & Gender Register (TH→EN)
Input:คุณครูคะ หนูขอถามหน่อยได้ไหมคะ ว่าการบ้านส่งวันไหนคะ (female student speaking to teacher, with polite particles คะ/หนู)
The launch of the Bangkok-Nonthaburi high-speed railway represents a significant milestone in Thailand's public transportation sector. The project, valued at over 150 billion baht, has taken more than eight years to construct and is expected to accommodate up to 500,000 passengers daily. In addition to alleviating severe traffic congestion on Phahonyothin Road, the railway will connect with the BTS and MRT rail systems at several key stations. The Governor of the State Railway of Thailand stated that, despite numerous challenges encountered during construction, the project's success reflects the dedication of the engineering team and the strong collaboration between the public and private sectors. From the day of its official opening, passengers will enjoy free access for the entire first month.
The launch of the Bangkok-Nonthaburi high-speed railway represents a significant milestone in Thailand's public transportation sector. The project, valued at over 150 billion baht, has taken more than eight years to construct and is expected to accommodate up to 500,000 passengers daily. In addition to alleviating severe traffic congestion on Phahonyothin Road, the railway will connect with the BTS and MRT rail systems at several key stations. The Governor of the State Railway of Thailand stated that, despite numerous challenges encountered during construction, the project's success reflects the dedication of the engineering team and the strong collaboration between the public and private sectors. From the day of its official opening, passengers will enjoy free access for the entire first month.
4bit (this)
The launch of the Bangkok-Nonthaburi high-speed railway marks a significant milestone in Thailand's public transportation system. The project, valued at over 150 billion baht, required more than eight years to construct and is expected to accommodate up to 500,000 passengers daily. In addition to alleviating severe traffic congestion on Phahonyothin Road, the railway will connect with the BTS and MRT systems at several key stations. The Governor of the State Railway of Thailand stated that, despite numerous challenges encountered during construction, the outcomes reflect the engineers' dedication and the collaborative efforts of both the public and private sectors. From the day of its opening, passengers will enjoy free service throughout the first month.
Observation: FP and Q8 are perfectly identical on long text. Q4 stays accurate (correct budget figure) but drifts on word choices: "marks" vs "represents", "required" vs "has taken", "free service" vs "free access".
Takeaway
bf16
8bit
4bit
Identical to FP
—
✅ mostly
⚠️ small drift
Name transliteration
✅
✅
⚠️ umlaut lost
Technical term casing
✅
✅
✅
Recommendation: For professional use, 8-bit is the sweet spot (99.3% fidelity, nearly identical output, half the size). For casual use, 4-bit is fine.
