Instructions to use ggml-org/MiMo-V2.6-Flash-RL-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 ggml-org/MiMo-V2.6-Flash-RL-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 ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4
# Run inference directly in the terminal:
llama cli -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

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 ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4
# Run inference directly in the terminal:
./llama-cli -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

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 ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

Use Docker

docker model run hf.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

LM Studio
Jan

vLLM

How to use ggml-org/MiMo-V2.6-Flash-RL-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ggml-org/MiMo-V2.6-Flash-RL-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": "ggml-org/MiMo-V2.6-Flash-RL-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

Ollama
How to use ggml-org/MiMo-V2.6-Flash-RL-GGUF with Ollama:
```
ollama run hf.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4
```
Unsloth Desktop

How to use ggml-org/MiMo-V2.6-Flash-RL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

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": "ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ggml-org/MiMo-V2.6-Flash-RL-GGUF with Docker Model Runner:
```
docker model run hf.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4
```

Lemonade

How to use ggml-org/MiMo-V2.6-Flash-RL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

Run and chat with the model

lemonade run user.MiMo-V2.6-Flash-RL-GGUF-MXFP4

List all available models

lemonade list

Hermes Agent

How to use ggml-org/MiMo-V2.6-Flash-RL-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 ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

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 ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ggml-org/MiMo-V2.6-Flash-RL-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4

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 "ggml-org/MiMo-V2.6-Flash-RL-GGUF:MXFP4" \
  --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"

ggerganov HF Staff commited on 11 days ago

Commit

cac6e14

verified ·

1 Parent(s): 9bf2e45

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

convert.log +310 -322
mtp-MiMo-V2.6-Flash-RL-BF16.gguf +1 -1
mtp-MiMo-V2.6-Flash-RL-MXFP4.gguf +1 -1
mtp-MiMo-V2.6-Flash-RL-Q8_0.gguf +1 -1

convert.log CHANGED Viewed

@@ -690,305 +690,293 @@ INFO:gguf.gguf_writer:upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00002-of
 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16.gguf
 + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-MiMo_V2.6_Flash_RL-PRIMARY --outtype bf16 --outfile ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf --mtp --model-name MiMo-V2.6-Flash-RL
 INFO:hf-to-gguf:Loading model: model-temp-MiMo_V2.6_Flash_RL-PRIMARY
@@ -1239,12 +1227,12 @@ INFO:gguf.gguf_writer:Writing the following files:
 INFO:gguf.gguf_writer:upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf: n_tensors = 39, total_size = 4.5G
 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf
 + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-MiMo_V2.6_Flash_RL-PRIMARY --outtype bf16 --outfile ./upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-BF16.gguf --mmproj --model-name MiMo-V2.6-Flash-RL
 INFO:hf-to-gguf:Loading model: model-temp-MiMo_V2.6_Flash_RL-PRIMARY
@@ -2143,12 +2131,12 @@ INFO:gguf.gguf_writer:Writing the following files:
 INFO:gguf.gguf_writer:upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-BF16.gguf: n_tensors = 811, total_size = 2.7G
 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-BF16.gguf
 + FLAGS_MXFP4=
 + llama.cpp/build/bin/llama-quantize --keep-split ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-MXFP4.gguf MXFP4_MOE
-version: 0.4.1-dev (build 11067, commit bc817a8bc)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf' to './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-MXFP4' as MXFP4_MOE
 llama_model_loader: additional 1 GGUFs metadata loaded.
@@ -2676,11 +2664,11 @@ llama_model_loader: - type mxfp4:  141 tensors
 llama_model_quantize_impl: model size  = 164915.57 MiB (4.48 BPW)
 llama_model_quantize_impl: quant size  = 159610.26 MiB (4.34 BPW)
-llama_quantize: quantize time = 580012.18 ms
-llama_quantize:    total time = 580012.18 ms
 + FLAGS_Q2_K='--pure     --tensor-type token_embd.weight=q8_0     --tensor-type output.weight=q6_k     --tensor-type attn_=q8_0     --tensor-type ffn_down_exps=mxfp4     --tensor-type ffn_gate_exps=q2_k     --tensor-type ffn_up_exps=q2_k '
 + llama.cpp/build/bin/llama-quantize --keep-split --allow-requantize --pure --tensor-type token_embd.weight=q8_0 --tensor-type output.weight=q6_k --tensor-type attn_=q8_0 --tensor-type ffn_down_exps=mxfp4 --tensor-type ffn_gate_exps=q2_k --tensor-type ffn_up_exps=q2_k ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-Q2_K.gguf MXFP4_MOE
-version: 0.4.1-dev (build 11067, commit bc817a8bc)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf' to './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-Q2_K' as MXFP4_MOE
 llama_model_loader: additional 1 GGUFs metadata loaded.
@@ -3400,10 +3388,10 @@ llama_tensor_get_type: blk.9.attn_qkv.weight                - applying manual ov
 llama_model_quantize_impl: model size  = 164915.57 MiB (4.48 BPW)
 llama_model_quantize_impl: quant size  = 119887.91 MiB (3.26 BPW)
-llama_quantize: quantize time = 1204756.57 ms
-llama_quantize:    total time = 1204756.57 ms
 + llama.cpp/build/bin/llama-quantize ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-MXFP4.gguf MXFP4_MOE
-version: 0.4.1-dev (build 11067, commit bc817a8bc)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf' to './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-MXFP4.gguf' as MXFP4_MOE
 llama_model_loader: loaded meta data with 42 key-value pairs and 39 tensors from ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf (version GGUF V3 (latest))
@@ -3494,10 +3482,10 @@ llama_model_loader: - type bf16:   20 tensors
 llama_model_quantize_impl: model size  =  4268.25 MiB (16.00 BPW)
 llama_model_quantize_impl: quant size  =  2267.63 MiB (8.50 BPW)
-llama_quantize: quantize time = 17083.67 ms
-llama_quantize:    total time = 17083.67 ms
 + llama.cpp/build/bin/llama-quantize ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-Q8_0.gguf Q8_0
-version: 0.4.1-dev (build 11067, commit bc817a8bc)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf' to './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-Q8_0.gguf' as Q8_0
 llama_model_loader: loaded meta data with 42 key-value pairs and 39 tensors from ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf (version GGUF V3 (latest))
@@ -3588,8 +3576,8 @@ llama_model_loader: - type bf16:   20 tensors
 llama_model_quantize_impl: model size  =  4268.25 MiB (16.00 BPW)
 llama_model_quantize_impl: quant size  =  2267.63 MiB (8.50 BPW)
-llama_quantize: quantize time =  3810.06 ms
-llama_quantize:    total time =  3810.06 ms
 + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-MiMo_V2.6_Flash_RL-PRIMARY --outtype q8_0 --outfile ./upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-Q8_0.gguf --mmproj --model-name MiMo-V2.6-Flash-RL
 INFO:hf-to-gguf:Loading model: model-temp-MiMo_V2.6_Flash_RL-PRIMARY
 WARNING:hf-to-gguf:Failed to load model config from model-temp-MiMo_V2.6_Flash_RL-PRIMARY: The repository model-temp-MiMo_V2.6_Flash_RL-PRIMARY contains custom code which must be executed to correctly load the model. You can inspect the repository content at /tmp/convert/model-temp-MiMo_V2.6_Flash_RL-PRIMARY .
@@ -4487,9 +4475,9 @@ INFO:gguf.gguf_writer:Writing the following files:
 INFO:gguf.gguf_writer:upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-Q8_0.gguf: n_tensors = 811, total_size = 1.6G
 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-Q8_0.gguf
 + echo MiMo-V2.6-Flash-RL-MXFP4-00001-of-00002.gguf
 + echo MiMo-V2.6-Flash-RL-MXFP4-00002-of-00002.gguf

 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16.gguf
 + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-MiMo_V2.6_Flash_RL-PRIMARY --outtype bf16 --outfile ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf --mtp --model-name MiMo-V2.6-Flash-RL
 INFO:hf-to-gguf:Loading model: model-temp-MiMo_V2.6_Flash_RL-PRIMARY
 INFO:gguf.gguf_writer:upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf: n_tensors = 39, total_size = 4.5G
 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf
 + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-MiMo_V2.6_Flash_RL-PRIMARY --outtype bf16 --outfile ./upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-BF16.gguf --mmproj --model-name MiMo-V2.6-Flash-RL
 INFO:hf-to-gguf:Loading model: model-temp-MiMo_V2.6_Flash_RL-PRIMARY
 INFO:gguf.gguf_writer:upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-BF16.gguf: n_tensors = 811, total_size = 2.7G
 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-BF16.gguf
 + FLAGS_MXFP4=
 + llama.cpp/build/bin/llama-quantize --keep-split ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-MXFP4.gguf MXFP4_MOE
+version: 0.5.0-dev (build 11161, commit a0484817c)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf' to './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-MXFP4' as MXFP4_MOE
 llama_model_loader: additional 1 GGUFs metadata loaded.
 llama_model_quantize_impl: model size  = 164915.57 MiB (4.48 BPW)
 llama_model_quantize_impl: quant size  = 159610.26 MiB (4.34 BPW)
+llama_quantize: quantize time = 567689.54 ms
+llama_quantize:    total time = 567689.54 ms
 + FLAGS_Q2_K='--pure     --tensor-type token_embd.weight=q8_0     --tensor-type output.weight=q6_k     --tensor-type attn_=q8_0     --tensor-type ffn_down_exps=mxfp4     --tensor-type ffn_gate_exps=q2_k     --tensor-type ffn_up_exps=q2_k '
 + llama.cpp/build/bin/llama-quantize --keep-split --allow-requantize --pure --tensor-type token_embd.weight=q8_0 --tensor-type output.weight=q6_k --tensor-type attn_=q8_0 --tensor-type ffn_down_exps=mxfp4 --tensor-type ffn_gate_exps=q2_k --tensor-type ffn_up_exps=q2_k ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf ./upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-Q2_K.gguf MXFP4_MOE
+version: 0.5.0-dev (build 11161, commit a0484817c)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-BF16-00001-of-00002.gguf' to './upload-MiMo_V2.6_Flash_RL/MiMo-V2.6-Flash-RL-Q2_K' as MXFP4_MOE
 llama_model_loader: additional 1 GGUFs metadata loaded.
 llama_model_quantize_impl: model size  = 164915.57 MiB (4.48 BPW)
 llama_model_quantize_impl: quant size  = 119887.91 MiB (3.26 BPW)
+llama_quantize: quantize time = 1227725.91 ms
+llama_quantize:    total time = 1227725.91 ms
 + llama.cpp/build/bin/llama-quantize ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-MXFP4.gguf MXFP4_MOE
+version: 0.5.0-dev (build 11161, commit a0484817c)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf' to './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-MXFP4.gguf' as MXFP4_MOE
 llama_model_loader: loaded meta data with 42 key-value pairs and 39 tensors from ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf (version GGUF V3 (latest))
 llama_model_quantize_impl: model size  =  4268.25 MiB (16.00 BPW)
 llama_model_quantize_impl: quant size  =  2267.63 MiB (8.50 BPW)
+llama_quantize: quantize time = 16883.06 ms
+llama_quantize:    total time = 16883.06 ms
 + llama.cpp/build/bin/llama-quantize ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-Q8_0.gguf Q8_0
+version: 0.5.0-dev (build 11161, commit a0484817c)
 built with GNU 14.2.0 for Linux x86_64
 llama_quantize: quantizing './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf' to './upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-Q8_0.gguf' as Q8_0
 llama_model_loader: loaded meta data with 42 key-value pairs and 39 tensors from ./upload-MiMo_V2.6_Flash_RL/mtp-MiMo-V2.6-Flash-RL-BF16.gguf (version GGUF V3 (latest))
 llama_model_quantize_impl: model size  =  4268.25 MiB (16.00 BPW)
 llama_model_quantize_impl: quant size  =  2267.63 MiB (8.50 BPW)
+llama_quantize: quantize time =  3866.49 ms
+llama_quantize:    total time =  3866.49 ms
 + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-MiMo_V2.6_Flash_RL-PRIMARY --outtype q8_0 --outfile ./upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-Q8_0.gguf --mmproj --model-name MiMo-V2.6-Flash-RL
 INFO:hf-to-gguf:Loading model: model-temp-MiMo_V2.6_Flash_RL-PRIMARY
 WARNING:hf-to-gguf:Failed to load model config from model-temp-MiMo_V2.6_Flash_RL-PRIMARY: The repository model-temp-MiMo_V2.6_Flash_RL-PRIMARY contains custom code which must be executed to correctly load the model. You can inspect the repository content at /tmp/convert/model-temp-MiMo_V2.6_Flash_RL-PRIMARY .
 INFO:gguf.gguf_writer:upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-Q8_0.gguf: n_tensors = 811, total_size = 1.6G
 INFO:hf-to-gguf:Model successfully exported to upload-MiMo_V2.6_Flash_RL/mmproj-MiMo-V2.6-Flash-RL-Q8_0.gguf
 + echo MiMo-V2.6-Flash-RL-MXFP4-00001-of-00002.gguf
 + echo MiMo-V2.6-Flash-RL-MXFP4-00002-of-00002.gguf

mtp-MiMo-V2.6-Flash-RL-BF16.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25a98efc0f9babd38a947a3ad6e56593606bba5cbf5e96f4aa525a7d20e1865
 size 4481536192

 version https://git-lfs.github.com/spec/v1
+oid sha256:a0ffc7356ce0ff8597f9d9b4e394df1fe68ee4726fa5867e7e99a9011c3c2293
 size 4481536192

mtp-MiMo-V2.6-Flash-RL-MXFP4.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c528610e42b6851ecd6fa5d8fef65d79bba50d269ff7b06f5f408605c6c3e9f1
 size 2383728832

 version https://git-lfs.github.com/spec/v1
+oid sha256:7be6df8a09060430b8ae4f106a127602a5ae8771c6d0e39e739ace0ad6083507
 size 2383728832

mtp-MiMo-V2.6-Flash-RL-Q8_0.gguf CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49d584ad8f33bea4e1344d3a5a2a57d63364412c0f6c36f4ba375efd1f43b26
 size 2383728832

 version https://git-lfs.github.com/spec/v1
+oid sha256:5f8f1c3a20a73d1dc68c83d21161121da0882f9e67d4c5c33fe5ef3f040233ca
 size 2383728832