Xing4.0-29B-A4B Text Generation Model: Our Test Answers, 24GB+ VRAM

September 28, 2026November 12, 2026

At a Glance

Values determined by this site’s code when the information was collected. Dates are JST.

What we checked ourselves

• Ran xing4_0-29b-iq2_M-slim.gguf (IQ2_M) on our CPU-only server (Neoverse-N1, 3 threads, llama.cpp b12210): generation at 4.5 tokens/s (a CPU figure, not a GPU speed).
• Its answers to our fixed Japanese questions are shown verbatim below.

Details and conditions are in “Our Own Measurements” below.

Overview

China Telecom’s AI subsidiary, China Telecom Artificial Intelligence Technology, has released a new large language model, Xing4.0-29B-A4B, on Hugging Face. It is a Mixture of Experts (MoE) model with a total of 29B parameters, of which only 4B are active per token. It handles a context length of 256K tokens by default, which can be extended to 512K tokens. Licensed under Apache-2.0, it is freely available including for commercial use.

Xing (Star) is the successor to models previously published by the company under the “TeleChat" name. The most significant feature of this release lies in its training infrastructure. According to the model card, Xing4.0-29B-A4B is the first model of this scale trained entirely on Huawei Ascend NPUs (Ascend 910C cluster) and the MindSpore framework. This means it achieved results matching leading open models of the same class on coding agent benchmarks without using NVIDIA GPUs.

The publisher has provided FP8 and GGUF versions directly alongside the weights (XingChen-AGI/Xing4.0-29B-A4B-FP8 and XingChen-AGI/Xing4.0-29B-A4B-GGUF). Because official GGUF files are available, it is easy to test using llama.cpp-based tools.

Specifications

Based on the model card configuration table:

• Parameter Count: Total 29B / Active 4B (MoE)
• Number of Layers: 40
• Hidden Dimension: 3,584
• FFN Intermediate Dimension: 9,216 for dense FFN, 1,024 per expert
• Experts: Uses 4 out of 64 routed experts, plus 1 always-on shared expert
• Attention: MLA (Multi-head Latent Attention)
• Context Length: 256K tokens (extendable up to 512K)
• Architectural Elements: The model card lists “mHC + MLA + MTP". MLA compresses the KV cache to reduce memory consumption in long contexts, while MTP (Multi-Token Prediction) simultaneously predicts multiple subsequent tokens and is also used to accelerate speculative decoding. The model card provides no formal name or explanation for mHC.
• Thinking Mode: The enable_thinking chat template parameter allows toggling whether to output the reasoning process.

Figures are also provided for training efficiency. By combining fine-grained MoE communication optimizations, selective recomputation, automatic operation fusion, and dedicated operators for mHC (Ascend C), training throughput on Ascend was reportedly increased by approximately 96% compared to unoptimized setups.

Performance

Transcribed directly from the model card’s evaluation table. The comparison targets are Gemma4-26B-A4B and Qwen3.6-35B-A3B, which have roughly the same scale of active parameters. All figures were measured by the publishers themselves.

Its strengths lie in agentic tasks that utilize tools and follow structured steps. Terminal-Bench 2.1, which tests the completion of tasks in a terminal, scores 57.50—outperforming Qwen3.6-35B-A3B (51.50) by 6 points and Gemma4-26B-A4B (30.00) by 27.5 points, making it the highest in the table. The overall agent evaluation Claw-Eval (76.55) and DeepresearchBII (60.80), which involves conducting extensive research to produce reports, are also the highest among the three models. SWE-bench Verified, which fixes bugs in real repositories, scores 75.00, essentially tying with Qwen3.6-35B-A3B at 76.00 and beating Gemma4-26B-A4B (53.00) by a 22-point margin.

On the other hand, it scores lowest in some categories. AA.LCR, which evaluates reading comprehension and reasoning over long documents, scores 61.00, falling short of both Gemma4-26B-A4B (66.00) and Qwen3.6-35B-A3B (62.00). Being able to handle a long context of 256K to 512K is distinct from accurately comprehending long contexts, and based on this table, the latter is weaker than the other two models in its class. Mathematics on AIME2026 (90.00) trails Qwen3.6-35B-A3B (92.70), and instruction-following on IFBench (69.67) falls behind Gemma4-26B-A4B (72.67). Tau3-Bench (64.63), which measures tool-using dialogues like customer service, is also lower than Qwen3.6-35B-A3B (67.20).

In summary, as a coding agent, it is equal to or better than Qwen3.6-35B-A3B and clearly superior to Gemma4-26B-A4B, while performing roughly on par with or slightly below the other two models in mathematics, long-text reading, and instruction following. Active parameters for all three models fall in the same 3B–4B bracket, providing a similar speed feel when run locally.

Evaluation conditions require caution. According to the model card footnotes, SWE-bench used the SWE-agent framework with a 210K token context, while Terminal-Bench 2.1 averaged 3 runs using the terminus-2 framework. It is not specified whether the two comparison models were measured under identical conditions.

Strengths and Use Cases

The model card envisions its use as the core of coding agents and general-purpose agents. It is designed to maintain multi-step planning, tool invocation, and long chains of reasoning even across extended contexts. The model card explicitly states that it has been aligned with agent frameworks such as OpenCode, Claude Code, OpenClaw, and Hermes, alongside output format integration.

Another intended use case is continual pre-training on proprietary data. It claims to enable low-cost adaptation for domain-specific applications such as intent classification, table understanding, contract review, and knowledge base Q&A. For continued training, it supports LLaMA-Factory and MindFormers, and deployment across multiple chips (including non-GPU hardware) is supported via BAAI’s FlagOS.

Recommended sampling settings are also provided by use case:

How It Differs from Similar Models

• Differences from Gemma4-26B-A4B: While active parameters are identically 4B, Xing outperforms Gemma by 15–27 points on coding agent benchmarks (SWE-bench Verified, Terminal-Bench 2.1, SWE-bench Multilingual). Conversely, Gemma scores higher on instruction following (IFBench) and long-text reading (AA.LCR).
• Differences from Qwen3.6-35B-A3B: Xing’s total parameter count is smaller by 6B. SWE-bench scores are nearly tied; Xing leads in Terminal-Bench 2.1, Claw-Eval, and DeepresearchBII, while Qwen leads in AIME2026, Tau3-Bench, and SWE-bench Multilingual. Strengths are divided, and neither model is universally superior.
• Training Infrastructure Differences: While the comparison models were trained on GPUs, Xing4.0 was trained exclusively on Ascend NPUs. From a user’s perspective, inference procedures remain unchanged, but it is significant as a demonstration that models of this class can be built on non-GPU training infrastructure.

Released under Apache-2.0 with official FP8 and GGUF versions provided concurrently, and with explicit support for agent frameworks, this release reflects an emphasis on making the model immediately usable by external developers rather than just publishing weights.

Hardware Requirements

Estimated requirements (calculated by Local Model Watch) — 31.2B parameters

Inference engine support (architecture name matched against each project’s own model registry in its source code, checked 2026-11-12): llama.cpp: registered, vLLM: not registered, MLX (mlx-lm): not registered. “Not registered" means the name is absent from that registry today, not that the model cannot run.

Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model’s authors. File sizes are measured from the converted build XingChen-AGI/Xing4.0-29B-A4B-GGUF. Compare with other models in our VRAM quick reference. What the quantization names mean: glossary.

Can You Run It Locally?

Runs in Ollama, LM Studio and llama.cpp via a converted build.

The publisher ships safetensors, but XingChen-AGI/Xing4.0-29B-A4B-GGUF provides a GGUF build you can use.

License — apache-2.0 (Commercial use allowed): Permits commercial use, modification and redistribution. Redistribution requires including the license and stating changes; includes a patent grant.

Compression: the IQ4_NL build measures 5.15 bits per weight — about 32% the size of the original 16-bit weights, calculated by this site from the actual file sizes.

Compiled by this site’s code from the published formats, converted builds we have found, and each engine’s own model registry. “Not found" means we have not seen such a build, not that none exists. License summaries are not legal advice — check the publisher’s original terms before relying on them.

Our Own Measurements

Values we measured ourselves on our server (no GPU) by actually reading and running this model’s files — not figures copied from the model card. How we measure, and the results for every model: Our Measurements.

What We Found

When running the XingChen-AGI/Xing4.0-29B-A4B model on a CPU with a low bit quantization, it successfully derived the correct answer for a word problem and generated emails and haiku, but failed to follow the sentence count instruction for summarization, resulting in the generation being cut off upon reaching the token limit. The generation speed was 4.46 tokens per second, which did not reach 6.19 tokens per second of Gryphe_Pantheon-Reasoning-26B-A4B-1.1-V2 measured under the same conditions, yet it operated faster than other models such as Signal-3.8-27B. Peak memory consumption recorded 12.7 GB, and because 4-bit was too large, measurements were conducted using the lower IQ2_M quantization. In the knowledge question, it failed to list any landlocked prefectures and mistakenly included a prefecture that faces the sea.

Inside the GGUF File

File: xing4_0-29b-IQ4_NL.gguf (18.72GB, IQ4_NL). We read only the header (metadata) of the file, not the weights.

The quant name in the file name describes the file as a whole; in practice layers mix several types. The average bits per weight is the measured file data divided by the number of weights.

Running It on a CPU Only

Conditions: Neoverse-N1, 3 threads, no GPU, llama.cpp b12210, IQ2_M (10.99GB) from XingChen-AGI/Xing4.0-29B-A4B-GGUF, measured 2026-11-09 (JST). The 4-bit files did not fit our 13GB limit, so we measured the lower-bit IQ2_M file; quality is lower than at 4 bits. Other models measured under the same conditions (closest in file size):

Peak memory includes the model file mapped into memory (mmap). A PC with a GPU will be much faster; these figures are a guide for CPU-only machines such as mini PCs and ARM boards.

Commands We Ran

We used the official llama.cpp build llama-b12210-bin-ubuntu-arm64.tar.gz from the releases page and downloaded these files:

https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B-GGUF/resolve/main/xing4_0-29b-iq2_M-slim.gguf

Speed (llama-bench):

nice -n 10 ./llama-bench -m xing4_0-29b-iq2_M-slim.gguf -t 3 -p 512 -n 128 -r 2 -o json

Answers: we started llama-server like this (we pick a free port each time; shown as 8080) and sent each question to /v1/chat/completions with the body below (only the question text changes; this example is the business-email question):

nice -n 10 ./llama-server -m xing4_0-29b-iq2_M-slim.gguf -t 3 -c 4096 --jinja --host 127.0.0.1 --port 8080 --no-mmproj

curl -s http://127.0.0.1:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d @- <<'EOF'
{
  "messages": [
    {
      "role": "user",
      "content": "取引先の担当者に、来週火曜日の打ち合わせを水曜日に変更してほしいとお願いするメールを、丁寧な敬語で書いてください。"
    }
  ],
  "temperature": 0,
  "seed": 0,
  "max_tokens": 1024,
  "chat_template_kwargs": {
    "enable_thinking": false
  }
}
EOF

Answers to Our Japanese Questions (Verbatim)

We ask every model the same five questions in Japanese under the conditions above (temperature 0, thinking turned off where the chat template allows it, up to 1024 tokens) and publish the answers unedited. We do not grade them; where a question has a single correct answer, we show it for comparison.

Summarization

次の記事を3文で要約してください。

みどり市は今年の春、市内に三つある公立図書館のうち最も古い中央図書館の改修を終え、十月一日に再開館した。改修は約一年半にわたり、総事業費は約十二億円。このうち約四億円は国の補助金でまかなわれた。

最大の変化は、閲覧席の配置である。以前は館内の座席の大半が学習用の机で、試験期間になると中高生で埋まり、高齢の利用者や小さな子ども連れが座れないという苦情が毎年寄せられていた。改修後は座席数を百二十席から二百席に増やしたうえで、学習用の机を三階にまとめ、一階は会話ができる「にぎわいフロア」、二階は静かに本を読む「閲覧フロア」に分けた。一階には予約制のグループ学習室が四室と、飲み物を持ち込めるカフェスペースも設けられた。

蔵書の面でも見直しが進んだ。貸出の少ない古い資料約三万冊を市内の他の館や保存書庫に移し、代わりに子ども向けの絵本と、介護・子育て・仕事探しといった暮らしに関わる実用書を約一万五千冊増やした。電子書籍の貸出サービスも始まり、利用登録をすれば自宅から一度に三冊まで、二週間借りられる。

建物そのものにも手が入った。築四十年を超えていた空調設備を入れ替え、屋上には太陽光パネルを設置して、館内で使う電力の約二割をまかなえるようにした。車いすの利用者から要望の多かったエレベーターは一基から二基に増え、書架の間の通路も以前より三十センチ広げられた。入口には段差のないスロープが新たに設けられ、授乳室と多目的トイレも各階に一つずつ置かれた。

一方で課題も残る。駐車場は改修前と同じ四十台のままで、週末には近くの道路に順番待ちの車が並んだ。市は隣接する市有地を臨時駐車場として開放したが、恒久的な対策は決まっていない。また、開館時間を平日の夜九時まで延ばしたことで職員の負担が増えており、職員団体は人員の追加を求めている。

利用者の受け止めはおおむね好意的だ。週に二度、孫を連れて来るという七十代の女性は「前は子どもが声を出すと周りの目が気になったが、一階なら気兼ねなく絵本を読んであげられる」と話す。一方、受験を控えた高校生の中には「学習席が三階だけになり、夕方はすぐに満席になる」と不満を漏らす人もいる。図書館は、学習席の空き状況をホームページで確認できる仕組みを年内に導入する予定だ。

再開館に合わせて、催しも増えた。毎週土曜の午前には読み聞かせ会、月に一度は地元の農家や商店主を講師に招く「まちの先生」講座が開かれる。十一月には、市内の中学生が選んだ本を紹介する展示も予定されている。

館長の山本和子さんは「本を借りる場所から、人が集まって過ごす場所へ変えたかった。再開館からの一か月で来館者は以前の一・八倍になった」と話す。市は来年度、残る二つの図書館についても利用者への聞き取りを行い、改修の必要性を検討する方針だ。

(Summarize the following article in three sentences. (The article, about 1,200 Japanese characters, describes the renovation and reopening of a city’s central library: the budget, the new floor layout and seating, changes to the collection and e-book lending, building and accessibility work, remaining issues such as parking and staff workload, users’ reactions, new events, and the city’s next steps.))

1. **分析请求：**
    *   **源文本：** 一篇关于绿市中央图书馆重新开放和翻修的简短新闻报道。
    *   **任务：** 将文本总结为三个句子（3文で要約）。

2. **分析源文本（提取关键信息）：**
    *   *第1句（背景与主要变化）：* 绿市中央图书馆在10月1日重新开放，耗时一年半，花费约12亿日元（其中4亿为政府补贴）。最大的变化是阅读区的重新布局：增加了120个座位至200个，将学习桌移至三楼，一楼设为“活力楼层”（可交谈），二楼设为“阅览楼层”（安静阅读），并设有咖啡区、小组学习室和婴儿哺乳室。
    *   *第2句（藏书与设施）：* 藏书也进行了调整：移除了约3万册借阅较少的旧资料，增加了约1.5万册实用书籍（儿童绘本、生活指南、就业/育儿信息）。此外，还开始了电子书借阅服务（最多可借3本，有效期2周）。建筑本身也得到了改善：更换了超过40年历史的空调系统，安装了太阳能电池板（提供约20%的电力），增加了电梯和更宽敞的书架通道，并设有无障碍坡道。
    *   *第3句（挑战与反响）：* 尽管如此，仍存在一些挑战：停车场容量未变（40个车位），周末交通拥堵；延长了开放时间至晚上9点，导致员工工作负担加重。然而，反应总体积极：老年人觉得一楼安静的环境适合读绘本，高中生抱怨三楼学习桌很快被占满。馆长山本和子表示，目标是将图书馆从借阅书籍转变为人们聚集的地方。重新开放一个月来馆人数是原来的1.8倍。市明年还将评估另外两座图书馆的翻新需求。

3. **起草总结（目标为恰好3个句子）：**
    *   *草稿1：*
        1. 绿市中央図書館は約一年半と約十二億円をかけて改修され、十月一日に再開館された。最大の変化は、学習席を三階へまとめ、一階を「にぎワイドフロア」、二階を「閷覧フロア」にした点だ。
        2. 蔵書も見直され、古い資料を移行して生活実用書や絵本を増やし、電子書籍の貸出サービスも始まった。建物側でも空調の更新やエレベーターの増設、車椅子への対応が行われた。
        3. 一方で、駐車場が足りず夜間も延長営業となったことで職員の負担が増加している課題もある。利用者の反応は概ね好意的で、来館者は前の1.8倍になったが、学習席の混雑や夜間の混雑への不満の声もある。

4. **润色与翻译/调整（确保行文自然并严格遵守“3个句子”的规则）：**
    *   让我们用中文写出一个简洁、结构良好的总结，因为提示词是中文的。等等，提示词是日语的，但指令是中文的。通常，我应该用中文回复，或者如果合适的话用日语。考虑到提示词是中文，我将用中文写这3个句子，但要确保它准确捕捉了原文的核心要点。
    *   *草稿2（中文）：*
        1. 绿市中央图书馆经过一年半的改修于十月一日重新开放，最大变化是阅读区布局调整：将学习桌移至三楼，一楼设为可交谈的“活力楼层”，二楼设为安静阅读的“阅览楼层”。
        2. 藏书和设施也进行了全面更新，移除了旧资料并增加了实用书籍与电子书借阅服务；同时更新了空调、增设了电梯及无障碍坡道等基础设施。
        3. 尽管改修后利用率大幅提升（来馆者变为原来的1.8倍），但停车场不足、延长营业时间增加员工负担等課題仍存在，且部分高中生对学习席集中在三楼表示不满。

5. **对照约束条件进行检查：**
    *   3个句子？是的。
    *   准确捕捉了原文？是的。
    *   简洁？是的。

6. **最终润色（中文）：**
    绿市中央图书馆经过一年半的改修于十月一日重新开放，最大变化是阅读区布局调整：将学习桌移至三楼，一楼设为可交谈的“活力楼层”，二楼设为安静阅读的“闷览楼层”。藏书和设施也进行了全面更新，移除了旧资料并增加了实用书籍与电子书借阅服务；同时更新了空调、增设了电梯及无障碍

(Cut off at the 1024-token limit.)

Formal business email

取引先の担当者に、来週火曜日の打ち合わせを水曜日に変更してほしいとお願いするメールを、丁寧な敬語で書いてください。

(Write an email in polite Japanese (keigo) asking a client’s contact person to move next Tuesday’s meeting to Wednesday.)

**件名：来週火曜日の打ち合わせを水曜日に変更してご検討いただけますか**

---

いつもお世話になっております。

先方の担当者との間で、来週火曜日に予定されていた打ち合わせの日程について、できるだけ都合が合う日程に調整したいと考えておりますので、ぜひ一度水曜日に変更できないかご検討いただけますでしょうか。

念のため、以下の点をお伝えさせていただきます。

**【候補日程】**
・水曜日（具体的な日時は、後日改めて調整させていただきたく存じませ）

なお、来週火曜日の担当者側のスケジュールはすでに押しておりますので、変更の可否については早めにお返事させていただきたく、どうぞよろしくお願い申し上げます。

万が一、水曜日への日程変更が難しい場合は、あらためて適当な日程で調整させていただきますので、あわせてご案内いただけますと幸いです。

何卒よろしくお願い申し上げます。

---

**【会社名】**
〇〇株式会社　〇〇部　〇〇〇
TEL：03-〇〇〇-〇〇〇〇　／　Mail：△△△@△△△.com

Word problem

りんごが1個120円、みかんが1個45円です。りんごを3個とみかんを8個買って、1,000円札で払いました。おつりはいくらですか。考え方も示してください。

(Apples cost 120 yen each and mandarins cost 45 yen each. You buy 3 apples and 8 mandarins and pay with a 1,000-yen bill. How much change do you get? Show your reasoning.)

# りんごとみかんを買ったときのおつり返し額を計算

## 価格の確認
- りんご：1個 120円
- みかん：1個 45円

## 買ったものの合計金額を計算

**りんご 3個の代金：**
$$3 \times 120 = 360 \text{ 円}$$

**みかん 8個の代金：**
$$8 \times 45 = 360 \text{ 円}$$

**合計金額：**
$$360 + 360 = 720 \text{ 円}$$

## おつり（戻額）を計算

$$1000 - 720 = 280 \text{ 円}$$

## 答え
おつりは **280円** です。

Reference: The correct answer is 280 yen (120×3 = 360, 45×8 = 360, 1,000 − 720 = 280).

Knowledge

日本の都道府県のうち、海に面していない県をすべて挙げてください。

(List all of Japan’s prefectures that do not border the sea.)

# 日本の海に面していない都道府県

日本は島国であるため、ほとんどの県が海に面していますが、以下の10の都府県は海に面していません。

1. **北海道**（渡と蝎蟻島など）
2. **四国**（直島など）
3. **沖�oken**（択冱島など）
4. **佐賴**（与上港など）
5. **琉留**（与嘉島など）
6. **九州**（大口町など）
7. **山梨**（笛川村など）
8. **静知**（知ノ里村など）
9. **都知**（神ノ崎町など）
10. **佐賀**（相知町など）

## 補足

※ 2023年時点では、一部の島帜については国際的に「海に面している」と判定される場合がありますが、日本国内では上記の10県が該当します。なお、近年の国境付近の島々の編れ替えなどにより、数は変動する可能性があります。

ただし、**佐蟊県**については、近年の国境の変更により「海に面していない」という説もありますので、一概には言えません。

Reference: The correct answer is eight prefectures: Tochigi, Gunma, Saitama, Yamanashi, Nagano, Gifu, Shiga and Nara.

Constrained writing

「春」をテーマにした俳句を3つ、五・七・五の音数を守って作ってください。それぞれに一言の説明を付けてください。

(Write three haiku on the theme of spring, keeping the 5-7-5 syllable pattern, each with a one-line explanation.)

# 春をテーマにした俵句

---

**1.**
窓拭きして春を見るけや、暖粞かす隙間より

（窓を拭いて春を見るようなものだ、暖窹（あんROID）が隙間から差す光が春。）

---

**2.**
菜の花揉みし里を来て、雪解け惜しからずや

（菜の花を揉んだ場所を訪れて、雪解けを詰り損じないようにとの意。）

---

**3.**
芽吹き立ち添う木の下、風や吹き返して散る声

（芽が吹き出した近い木の下を、風が返して散らばせる音。）

---

## 解説

- **句1**：「暖窹（あんROID）」は「暖縏（あんROID）」とも呼ばれる春の陽ざしを指す。窓を拭いて春を発見する所作が、春への気づきを促す。
- **句2**：菜の花畑を訪れ、「雪解けを詰り（こぼさず）」ようにと、春の喜びを控えた表現で、季語としての「春」を凝らした一句。
- **句3**：芽吹く草木の下で、風が葉を返して散らばせる音＝「散る声」が春の情景を生きる。

Recent Models in the Same Size Class

Models with 15–40B parameters that Local Model Watch covered recently, listed by code from our article log for comparison. VRAM tiers are this site’s estimates; licenses are as stated on the model cards.

How to Get It

• Distribution Format: Transformers-format (safetensors) weights are available at XingChen-AGI/Xing4.0-29B-A4B on Hugging Face. Official FP8 and GGUF versions are hosted in separate repositories. It is also distributed on ModelScope and Modelers.
• Example Download Command: huggingface-cli download XingChen-AGI/Xing4.0-29B-A4B
• Supported Engines: The model card lists vLLM, SGLang, and KTransformers, with startup procedures provided in the GitHub repository. Note that inference examples using GitHub’s Transformers require trust_remote_code=True, executing the code bundled within the repository.
• Running Locally: Using the official GGUF version allows testing with llama.cpp-based tools. Computational workload per token corresponds to 4 active parameters, making generation faster than dense models of the same total parameter count. However, sufficient memory must be available to load all 29B parameters. Refer to the table below for estimated memory requirements.

Quantized and Converted Variants

File sizes of each build:

• Available builds in XingChen-AGI/Xing4.0-29B-A4B-GGUF: IQ4_NL 18.7GB
• Available builds in XingChen-AGI/Xing4.0-29B-A4B-FP8: FP8 30.9GB
• Available builds in mlx-community/Xing4.0-29B-A4B-OptiQ-4bit: MLX 4bit 19.2GB

In addition, 12 converted build(s) from other uploaders exist on Hugging Face; this site lists only builds from the model’s publisher or established quantization maintainers.

This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files. What the quantization names mean: glossary.

Other Models for the Same Task

Recent text generation models covered by Local Model Watch, newest first. Grouped by the task each publisher declares on Hugging Face (pipeline_tag); the smallest VRAM tier is this site’s estimate.

• Naive-N0.5-Flash MoE Model for AI Research and Coding: ~690GB Memory (Over 80GB)
• LFM2.5-350M-Diffusion-Exp Text Generation Model: 4GB+ VRAM (425M, 4GB)
• Xiaomi Releases MiMo-V2.6-Flash-MOPD and Pro-MOPD Models
• MiMo-V2.6-Pro-RL Text Generation Model: ~417GB Memory, GGUF Builds (Over 80GB)

See all text generation models →

What to Read Next

• Find models by VRAM (This model runs from the 24GB tier) → Other models that run on a 24GB GPU
• Explore the same model family → Xing4.0 family overview (1 articles, 3 converted builds)
• Engines that run this model → llama.cpp / Ollama
• What IQ4_NL mean and where to get this model → GGUF format guide and models / MLX format guide and models / FP8 format guide and models / Quantization and model-format glossary
• Learn about the publisher → China Telecom (Xing, TeleChat): models, licenses and articles

Sources

• https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B
• https://github.com/XingChen-AGI/Xing4.0-29B-A4B

Update History

• 2026-09-28: Added converted builds to “Quantized and Converted Variants”: XingChen-AGI/Xing4.0-29B-A4B-GGUF, XingChen-AGI/Xing4.0-29B-A4B-FP8, mlx-community/Xing4.0-29B-A4B-OptiQ-4bit
• 2026-09-28: Updated the hardware requirements table with the actual file sizes of XingChen-AGI/Xing4.0-29B-A4B-GGUF.
• 2026-09-28: Changed the title to show what the article covers (VRAM requirements, file list, etc.).
• 2026-09-28: Added our own measurements: what is inside the GGUF file.
• 2026-09-30: Added our own measurements: VRAM and answers to Japanese questions with the publisher’s own code.
• 2026-09-30: Changed the title to show what the article covers (VRAM requirements, file list, etc.).
• 2026-11-09: Added our own measurements: CPU speed and answers to Japanese questions.