Add files using upload-large-folder tool

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

MiMo-V2.5-coder-Q2-00001-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400d2928a0863f8e338717bdfc9d826cae7049ff968a79ac7b1220ebb93552f8
+size 8831584256

MiMo-V2.5-coder-Q2-00002-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3820d01f8aac9c26b0430d4c3feef68fb5d02b8304418f5a994de6359b9ba94
+size 6996099872

MiMo-V2.5-coder-Q2-00003-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1043df380f9859dd1f42eea9862fbfd5987c737a679dc57941c8e6b52535a8bd
+size 6996099872

MiMo-V2.5-coder-Q2-00004-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6834f524a2f2de1153a11ba5f9509bd6268a240f891bf2dc4d311c52ee3f3e56
+size 6996099872

MiMo-V2.5-coder-Q2-00005-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f50e2e0a565dc9dd67e45b6f1a6709bfe60e7f9918ef4e2e6f0ef300e43a98c
+size 6996099872

MiMo-V2.5-coder-Q2-00006-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88743a58cb0f6db6c96c26e8fdfc6973b2f73c4250d7b79b1cb11f4ff3f93999
+size 6996099872

MiMo-V2.5-coder-Q2-00007-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:472170a584ab7edbdf31bc8ccc8f998214de9aaf18355708c8df35b999c5f371
+size 6996099872

MiMo-V2.5-coder-Q2-00008-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22650e6f26ea15f6d76d467e910fe31ba46cc7423d83aaf73922d2599bac33a4
+size 6996099872

MiMo-V2.5-coder-Q2-00009-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df50089f1d5263d77e63ff6a6cc9856bf19b4d195cb6fc849eb109a3bbe867f5
+size 6996099872

MiMo-V2.5-coder-Q2-00010-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6affc7d53669b35aca07ae7b057ddb3508120f5676115fca4022ead75899002
+size 6996099872

MiMo-V2.5-coder-Q2-00011-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1be676dcfea5791849cf67086e14b2d3b756d4d40abcdac179ce7316f5297b
+size 6996099872

MiMo-V2.5-coder-Q2-00012-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a14699f5394d85069574f49a93b6cc26643c3d3f6e7673e32bf756291ff02df2
+size 6996099872

MiMo-V2.5-coder-Q2-00013-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45d32e0266cb277a6fff36e19a8174d4118975a0ae7c5233fef9efdf0cbb97d
+size 6996099872

MiMo-V2.5-coder-Q2-00014-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b24c23aa55751b4a095ffa5e90165e6bd868a155885ed838878eea0963fa640
+size 6996099840

MiMo-V2.5-coder-Q2-00015-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22efbfcbd2c4287944b2cdc9dd3473430ce6ed247ad83118d8fb32c6ddf7ad3
+size 6996099872

MiMo-V2.5-coder-Q2-00016-of-00016.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35051041037ab14d47c7e72502d8b19bf52832134c164acbb72b9e96bfba219e
+size 6996099872

README.md

@@ -0,0 +1,224 @@
+---
+license: mit
+base_model: XiaomiMiMo/MiMo-V2.5
+language:
+- en
+library_name: llama.cpp
+tags:
+- gguf
+- llama.cpp
+- text-generation
+- code
+- tool-calling
+- agent
+- mixture-of-experts
+- long-context
+pipeline_tag: text-generation
+---
+
+# MiMo-V2.5 Coder Q2 GGUF
+
+This is a local, self-quantized GGUF build of [XiaomiMiMo/MiMo-V2.5](https://huggingface.co/XiaomiMiMo/MiMo-V2.5), tuned for coding and tool-calling on a 128 GB Apple Silicon M5 machine.
+
+This quant was optimized for systems with 128 GB of memory. The default serving profile targets a 128 GB Apple Silicon machine and tries to keep the model practical at a 100,000-token context. Smaller-memory systems will likely need more aggressive CPU offload, a smaller context, or a different quant.
+
+It is a text-only llama.cpp conversion of the MiMo language backbone. The original MiMo-V2.5 checkpoint is omnimodal, but this GGUF does not include the vision or audio encoders. The MiMo multi-token prediction blocks were also omitted during conversion because normal llama.cpp generation does not currently execute them for this model.
+
+## Files
+
+The model is split into 16 GGUF shards:
+
+```text
+MiMo-V2.5-coder-Q2-00001-of-00016.gguf
+...
+MiMo-V2.5-coder-Q2-00016-of-00016.gguf
+```
+
+Load the first shard. llama.cpp will find the remaining shards automatically.
+
+## Quantization
+
+This artifact was quantized from the original XiaomiMiMo checkpoint, not from a third-party GGUF.
+
+High-level summary:
+
+- Quant type: `Q2_K_S`
+- Importance matrix: coding and tool-calling focused
+- Preserved higher precision for embeddings, output, attention, and the dense first FFN
+- MoE down-expert tensors: `Q3_K`
+- Reported quantized size: about 108,496.76 MiB at 2.95 BPW
+
+One tokenizer metadata fix is included so llama.cpp does not warn about the base-vocab `</s>` token at load time. MiMo's actual EOS token remains `<|im_end|>`.
+
+## Importance Matrix
+
+The importance matrix is what makes this quant more targeted than a generic low-bit conversion.
+
+It was built from English coding and agent-style prompts: reading files, searching code, running shell commands, editing workflows, short code review tasks, and OpenAI-compatible tool calls. The tool-call calibration included realistic argument shapes such as bounded file reads, tail reads, grep context lines, and command arrays.
+
+That means the quantization tries to spend its limited precision budget on weights that matter for coding and structured tool use. It is not a general-purpose multilingual calibration set, and it was not designed to preserve Chinese or multimodal quality.
+
+## Why This Quant Exists
+
+The goal is not to preserve every capability of the original model equally. This build deliberately prioritizes:
+
+- reliable OpenAI-compatible tool calls
+- coding and shell-oriented agent use
+- English prompts and codebase work
+- practical inference on a 128 GB Apple Silicon system
+
+Chinese-language quality and multimodal use were not optimization targets.
+
+## Serving
+
+Install or build llama.cpp with `llama-server` available in `PATH`. Once the model is on Hugging Face, the usual way to run it is directly from the Hub:
+
+```sh
+llama-server \
+  -hf jedisct1/MiMo-V2.5-coder-Q2 \
+  --host 127.0.0.1 \
+  --port 8080 \
+  --ctx-size 100000 \
+  --parallel 1 \
+  --batch-size 512 \
+  --ubatch-size 128 \
+  --threads 12 \
+  --threads-batch 18 \
+  --prio 0 \
+  --poll 80 \
+  --flash-attn on \
+  --jinja \
+  --fit on \
+  --fit-target 4096 \
+  --fit-ctx 100000 \
+  --gpu-layers auto \
+  --cache-type-k f16 \
+  --cache-type-v f16 \
+  --reasoning off
+```
+
+This starts an OpenAI-compatible server on `127.0.0.1:8080`. The repository contains one GGUF split set, so recent llama.cpp builds should select the first shard automatically.
+
+If your llama.cpp build does not auto-select the split file, point it at the first shard explicitly:
+
+```sh
+llama-server \
+  -hf jedisct1/MiMo-V2.5-coder-Q2 \
+  --hf-file MiMo-V2.5-coder-Q2-00001-of-00016.gguf
+```
+
+If you cloned or downloaded the repository locally, you can use the included helper script instead:
+
+```sh
+./run-server.sh
+```
+
+The script uses the same defaults and loads the first GGUF shard from the repository directory.
+
+Default serving settings:
+
+```sh
+MIMO_CTX=100000
+MIMO_FIT_CTX=100000
+MIMO_FIT_TARGET=4096
+MIMO_BATCH=512
+MIMO_UBATCH=128
+MIMO_REASONING=off
+MIMO_CPU_MOE=0
+```
+
+These defaults are tuned for an Apple M5 Max with 128 GB unified memory. They keep reasoning output disabled, use the model's Jinja chat template, use Flash Attention, and ask llama.cpp to fit as much of the model as possible onto Metal.
+
+If you hit memory pressure, use the safer CPU-MoE mode:
+
+```sh
+MIMO_CPU_MOE=1 MIMO_FIT_TARGET=32768 MIMO_BATCH=128 MIMO_UBATCH=64 ./run-server.sh
+```
+
+That mode is slower, especially on long prompt prefill, but it leaves much more Metal memory headroom.
+
+You can point directly at a different `llama-server` binary with:
+
+```sh
+LLAMA_SERVER=/path/to/llama-server ./run-server.sh
+```
+
+You can also run `llama-server` directly against local files without the helper script:
+
+```sh
+llama-server \
+  --model MiMo-V2.5-coder-Q2-00001-of-00016.gguf \
+  --host 127.0.0.1 \
+  --port 8080 \
+  --ctx-size 100000 \
+  --parallel 1 \
+  --batch-size 512 \
+  --ubatch-size 128 \
+  --threads 12 \
+  --threads-batch 18 \
+  --prio 0 \
+  --poll 80 \
+  --flash-attn on \
+  --jinja \
+  --fit on \
+  --fit-target 4096 \
+  --fit-ctx 100000 \
+  --gpu-layers auto \
+  --cache-type-k f16 \
+  --cache-type-v f16 \
+  --reasoning off
+```
+
+For the safer CPU-MoE fallback, add `--cpu-moe` and use a larger fit margin:
+
+```sh
+llama-server \
+  --model MiMo-V2.5-coder-Q2-00001-of-00016.gguf \
+  --ctx-size 100000 \
+  --fit on \
+  --fit-target 32768 \
+  --fit-ctx 100000 \
+  --batch-size 128 \
+  --ubatch-size 64 \
+  --flash-attn on \
+  --jinja \
+  --gpu-layers auto \
+  --cache-type-k f16 \
+  --cache-type-v f16 \
+  --reasoning off \
+  --cpu-moe
+```
+
+## Tool-Calling Notes
+
+For best tool-calling results:
+
+- Use OpenAI-compatible request-provided tool schemas.
+- Keep llama.cpp built-in tools disabled unless you are specifically testing them.
+- Disable model reasoning output with `--reasoning off` or `MIMO_REASONING=off`.
+- Set `parallel_tool_calls` to `false` if your client supports it.
+- Avoid forcing `tool_choice: required`; in testing it made malformed calls more likely.
+
+This build was tested with Swival-style tool schemas for `read_file`, `grep`, `outline`, `run_command`, and `todo`.
+
+## Local Test Results
+
+On the local 128 GB Apple Silicon M5 setup:
+
+- The first local `Q2_K` artifact passed only 5/7 in its best Swival-shaped serving configuration.
+- This imatrix-backed `Q2_K_S` artifact passed 21/21 across three Swival-shaped repeat runs with fast M5 serving defaults.
+- A Swival-style `Hello` request rendered to 4,411 prompt tokens because the client included a system prompt and tool schemas. With fast M5 serving, llama.cpp processed that payload at about 239 prompt tokens/sec. With all MoE tensors on CPU, the same class of prompt processed at about 13 prompt tokens/sec.
+
+These are local smoke and agent-harness results, not a public benchmark suite.
+
+## Limitations
+
+- Text-only GGUF: no vision, video, or audio encoders.
+- MTP blocks are omitted.
+- The quantization is very low bit. It is intended to fit and run locally, not to match the full BF16 checkpoint.
+- The default 100,000-token context is much smaller than MiMo-V2.5's advertised 1M training context, but much more practical on this hardware.
+- Quality should be validated on your own coding and tool-calling workloads before relying on it.
+
+## License
+
+The upstream model card for `XiaomiMiMo/MiMo-V2.5` declares the MIT license. This derived GGUF is provided under the same license metadata.

run-server.sh

@@ -0,0 +1,62 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)
+LLAMA_SERVER=${LLAMA_SERVER:-llama-server}
+
+if ! command -v "$LLAMA_SERVER" >/dev/null 2>&1; then
+  echo "llama-server was not found. Install llama.cpp or set LLAMA_SERVER=/path/to/llama-server." >&2
+  exit 1
+fi
+
+if [[ -n "${MIMO_MODEL:-}" ]]; then
+  MODEL=$MIMO_MODEL
+else
+  shopt -s nullglob
+  CANDIDATES=("$SCRIPT_DIR"/MiMo-V2.5-coder-Q2-00001-of-*.gguf)
+  shopt -u nullglob
+
+  if [[ ${#CANDIDATES[@]} -eq 0 ]]; then
+    echo "No first GGUF shard found next to run-server.sh." >&2
+    exit 1
+  fi
+
+  MODEL=${CANDIDATES[0]}
+fi
+
+ARGS=(
+  --model "$MODEL"
+  --host "${MIMO_HOST:-127.0.0.1}"
+  --port "${MIMO_PORT:-8080}"
+  --ctx-size "${MIMO_CTX:-100000}"
+  --parallel "${MIMO_PARALLEL:-1}"
+  --batch-size "${MIMO_BATCH:-512}"
+  --ubatch-size "${MIMO_UBATCH:-128}"
+  --threads "${MIMO_THREADS:-12}"
+  --threads-batch "${MIMO_THREADS_BATCH:-18}"
+  --prio "${MIMO_PRIO:-0}"
+  --poll "${MIMO_POLL:-80}"
+  --flash-attn on
+  --jinja
+  --fit "${MIMO_FIT:-on}"
+  --fit-target "${MIMO_FIT_TARGET:-4096}"
+  --fit-ctx "${MIMO_FIT_CTX:-100000}"
+  --gpu-layers "${MIMO_GPU_LAYERS:-auto}"
+  --cache-type-k "${MIMO_CACHE_K:-f16}"
+  --cache-type-v "${MIMO_CACHE_V:-f16}"
+  --reasoning "${MIMO_REASONING:-off}"
+)
+
+if [[ "${MIMO_CPU_MOE:-0}" == "1" ]]; then
+  ARGS+=(--cpu-moe)
+fi
+
+if [[ -n "${MIMO_DEVICE:-}" ]]; then
+  ARGS+=(--device "$MIMO_DEVICE")
+fi
+
+if [[ -n "${MIMO_TOOLS:-}" ]]; then
+  ARGS+=(--tools "$MIMO_TOOLS")
+fi
+
+exec "$LLAMA_SERVER" "${ARGS[@]}" "$@"