Skip to content
localllm
日本語

ISTA-DASLab

Qwen3.8-Flash-Next-GSQ-RCO-Coder

Image input

Parameters
116.5B
Max context length
262,144
Architecture
qwen4exp
License
Conditional
Base model
Qwen/Qwen3.8-Flash-Next
License
apache-2.0
llama.cpp
b10660+

About Qwen3.8-Flash-Next-GSQ-RCO-Coder

Qwen3.8-Flash-Next-GSQ-RCO-Coder is a GGUF model based on Qwen/Qwen3.8-Flash-Next on Hugging Face. GGUF files are published by ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF. It has about 116.5B parameters, the qwen4exp architecture, a maximum context length of 262,144 tokens (values written in the GGUF).

There is one quantization, IQ1_M, with a file size of 58.4 GB (actual size on Hugging Face).

Running IQ1_M (58.4 GB) with an 8,192-token context needs an estimated 59.8 GB of memory, and an estimated 60.5 GB at 32,768 tokens. For 8,192 tokens, a GPU with 64 GB or more of VRAM, or a Mac with 64 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom).

The original model is licensed under Qwen Community License 1.0, which allows commercial use with conditions such as scale or purpose. Check the original license for the terms of use. An mmproj file for image input is also available.

File size and estimated memory per quantization

  • Up to 8 GB
  • Up to 16 GB
  • Up to 24 GB
  • Up to 48 GB
  • Up to 128 GB
  • More

File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.

All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).

Using image input: This model supports image input. To use images, an mmproj file is loaded as well.

About the "quality guide" (how far a quantization drifts from the original)

For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.

The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).

These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".

Quantization Quality guide KLD (no imatrix) KLD (imatrix) Size (Llama-3-8B)
Q8_0 Nearly identical 0.0014 - 7.96 GiB
Q6_K Very small 0.0055 - 6.14 GiB
Q5_K_M Very small 0.0108 - 5.33 GiB
Q5_K_S Small 0.0166 - 5.21 GiB
Q5_1 Small 0.0180 - 5.65 GiB
Q5_0 Small 0.0222 - 5.21 GiB
Q4_K_M Small 0.0313 0.0282 4.58 GiB
Q4_K_S Medium 0.0431 0.0320 4.37 GiB
IQ4_NL Small - 0.0357 4.35 GiB
IQ4_XS Small - 0.0363 4.14 GiB
Q4_1 Medium 0.0717 - 4.78 GiB
Q4_0 Medium 0.0719 - 4.34 GiB
Q3_K_L Medium 0.0872 0.0731 4.03 GiB
Q3_K_M Medium 0.1019 0.0844 3.74 GiB
IQ3_M Medium - 0.1025 3.53 GiB
IQ3_S Medium - 0.1113 3.42 GiB
IQ3_XS Large - 0.1387 3.28 GiB
IQ3_XXS Large - 0.1836 3.05 GiB
Q3_K_S Large 0.2282 0.1998 3.41 GiB
IQ2_M Large - 0.3260 2.74 GiB
Q2_K Very large 0.4451 0.3322 2.96 GiB
Q2_K_S Very large - 0.4034 2.96 GiB
IQ2_S Very large - 0.4392 2.56 GiB
IQ2_XS Very large - 0.5463 2.43 GiB
IQ2_XXS Very large - 0.8120 2.24 GiB
IQ1_M Very large - 1.3931 2.01 GiB
IQ1_S Very large - 2.2546 1.88 GiB

Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations

GGUF source

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

Published by the original developer About this label

Last checked: Nov 11, 2026

Architecture
qwen4exp
llama.cpp b10660 and later
Parameters
116.5B
Max context length
262,144
License
qwen-community-1.0 Conditional
File size and memory per quantization for Qwen3.8-Flash-Next-GSQ-RCO-Coder (ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF)
Quantization File size Measured Quality guide 4,096 8,192 16,384 32,768 65,536 131,072 262,144 max
IQ1_M (2 parts) 58.4 GB Very large 59.7 GB 59.8 GB 60.0 GB 60.5 GB 61.4 GB 63.2 GB 66.8 GB

The mmproj file for image input (BF16) is 0.91 GB Measured . It is not included in the memory above, so add it if you use images. 

Ollama  ollama run hf.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M
llama.cpp  llama-server -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

License and commercial use

Qwen Community License 1.0 Conditional

Allows commercial use. However, companies (including affiliates) that offer the model to third parties as a service (Model as a Service, e.g. via an API) or run an AI assistant business for coding or office work need a separate license from Qwen before commercial use (internal-only use is excluded). Products with over 100 million monthly active users or over USD 20 million in monthly revenue must display the model name.

Based on the license on the original model's Hugging Face page. This differs from the GGUF repository's label (apache-2.0). Quantized files are made from the original model, so check the original model's license terms as well. Original license text (checked Oct 18, 2026)

The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses

How to run

Mainline llama.cpp can load this model's format (qwen4exp) from b10660 (Aug 27, 2026) onward. Ollama and LM Studio bundle llama.cpp internally, so an older app fails to load it with errors such as "unknown model architecture". If that happens, update the app.

Example commands using IQ1_M. To use another quantization, replace the name with one from the table above. How to run local LLMs

Ollama

Run it by pointing directly at the GGUF on Hugging Face.

ollama run hf.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

llama.cpp

Pass the repository and quantization name to llama-server (or llama-cli) with -hf.

llama-server -hf ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M

LM Studio

Paste ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF into the search box, download it, and choose the quantization from the file list.

Frequently asked questions

How much memory do I need to run Qwen3.8-Flash-Next-GSQ-RCO-Coder (IQ1_M)?
The file size is 58.4 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 59.8 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
Can Qwen3.8-Flash-Next-GSQ-RCO-Coder be used commercially?
The original model's license is Qwen Community License 1.0 (Commercial use with conditions).Allows commercial use. However, companies (including affiliates) that offer the model to third parties as a service (Model as a Service, e.g. via an API) or run an AI assistant business for coding or office work need a separate license from Qwen before commercial use (internal-only use is excluded). Products with over 100 million monthly active users or over USD 20 million in monthly revenue must display the model name. Check the original license text before deciding.
Does Qwen3.8-Flash-Next-GSQ-RCO-Coder run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
8 GB: no quantization fits; 12 GB: no quantization fits; 16 GB: no quantization fits; 24 GB: no quantization fits (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
What is the command to run Qwen3.8-Flash-Next-GSQ-RCO-Coder with Ollama?
Run "ollama run hf.co/ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF:IQ1_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.