Qwen
Qwen3.8-Flash-Next
Image input
- Parameters
- 176.9B
- Max context length
- 262,144
- Architecture
- qwen4exp
- License
- Conditional
- Base model
- Qwen/Qwen3.8-Flash-Next
- License
- qwen-community-1.0
- llama.cpp
- b10660+
About Qwen3.8-Flash-Next
Qwen3.8-Flash-Next is a GGUF model based on Qwen/Qwen3.8-Flash-Next on Hugging Face. GGUF files are published by 5 sources (unsloth/Qwen3.8-Flash-Next-GGUF, AtomicChat/Qwen3.8-Flash-Next-GGUF, ggml-org/Qwen3.8-Flash-Next-GGUF and others). It has about 176.9B parameters, the qwen4exp architecture, a maximum context length of 262,144 tokens (values written in the GGUF).
There are 39 quantizations, with file sizes from 66.4 GB (UD-IQ1_S) to 354 GB (BF16) (actual sizes on Hugging Face).
Running UD-IQ1_S (66.4 GB) with an 8,192-token context needs an estimated 67.8 GB of memory, and an estimated 68.4 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).
5 sources publish GGUF files of this model. Quantization types and file sizes differ slightly between sources, so there is a table for each source below.
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
unsloth/Qwen3.8-Flash-Next-GGUF
Converted and published by a third party About this label
Last checked: Nov 11, 2026
- Architecture
- qwen4exp
- llama.cpp b10660 and later
- Parameters
- 176.9B
- Max context length
- 262,144
- License
- qwen-community-1.0 Conditional
| Quantization | File size Measured | Quality guide | 4,096 | 8,192 | 16,384 | 32,768 | 65,536 | 131,072 | 262,144 max |
|---|---|---|---|---|---|---|---|---|---|
| UD-IQ1_S (3 parts) | 66.4 GB | - | 67.7 GB | 67.8 GB | 68.0 GB | 68.4 GB | 69.4 GB | 71.2 GB | 74.8 GB |
| UD-IQ1_M (3 parts) | 68.0 GB | - | 69.3 GB | 69.4 GB | 69.6 GB | 70.1 GB | 71.0 GB | 72.8 GB | 76.4 GB |
| UD-Q2_0 (3 parts) | 70.5 GB | - | 71.8 GB | 71.9 GB | 72.2 GB | 72.6 GB | 73.5 GB | 75.3 GB | 79.0 GB |
| UD-IQ2_XS (3 parts) | 75.8 GB | - | 77.1 GB | 77.2 GB | 77.4 GB | 77.9 GB | 78.8 GB | 80.6 GB | 84.2 GB |
| UD-Q2_K_XL (4 parts) | 79.6 GB | - | 80.9 GB | 81.0 GB | 81.2 GB | 81.7 GB | 82.6 GB | 84.4 GB | 88.0 GB |
| UD-IQ3_XXS (4 parts) | 83.6 GB | - | 84.9 GB | 85.0 GB | 85.2 GB | 85.7 GB | 86.6 GB | 88.4 GB | 92.0 GB |
| UD-Q3_K_XL (4 parts) | 89.5 GB | - | 90.7 GB | 90.9 GB | 91.1 GB | 91.5 GB | 92.4 GB | 94.3 GB | 97.9 GB |
| UD-IQ4_XS (4 parts) | 93.7 GB | - | 94.9 GB | 95.1 GB | 95.3 GB | 95.7 GB | 96.6 GB | 98.5 GB | 102 GB |
| UD-Q4_K_XL (4 parts) | 111 GB | - | 113 GB | 113 GB | 113 GB | 113 GB | 114 GB | 116 GB | 120 GB |
| UD-Q5_K_XL (6 parts) | 158 GB | - | 160 GB | 160 GB | 160 GB | 160 GB | 161 GB | 163 GB | 167 GB |
| UD-Q6_K_XL (6 parts) | 169 GB | - | 170 GB | 171 GB | 171 GB | 171 GB | 172 GB | 174 GB | 178 GB |
| Q8_0 (6 parts) | 188 GB | Nearly identical | 190 GB | 190 GB | 190 GB | 190 GB | 191 GB | 193 GB | 197 GB |
| BF16 (8 parts) | 354 GB | Original precision | 355 GB | 355 GB | 356 GB | 356 GB | 357 GB | 359 GB | 362 GB |
The mmproj file for image input (F16) is 0.90 GB Measured . It is not included in the memory above, so add it if you use images.
Ollama ollama run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S
llama.cpp llama-server -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S
GGUF source
AtomicChat/Qwen3.8-Flash-Next-GGUF
Converted and published by a third party About this label
Last checked: Nov 11, 2026
- Architecture
- qwen4exp
- llama.cpp b10660 and later
- Parameters
- 176.9B
- Max context length
- 262,144
- License
- qwen-community-1.0 Conditional
| Quantization | File size Measured | Quality guide | 4,096 | 8,192 | 16,384 | 32,768 | 65,536 | 131,072 | 262,144 max |
|---|---|---|---|---|---|---|---|---|---|
| IQ4_XS (3 parts) | 84.9 GB | Small | 86.2 GB | 86.3 GB | 86.5 GB | 87.0 GB | 87.9 GB | 89.7 GB | 93.3 GB |
| Q4_K_M (3 parts) | 94.5 GB | Small | 95.8 GB | 95.9 GB | 96.1 GB | 96.6 GB | 97.5 GB | 99.3 GB | 103 GB |
| Q5_K_M (3 parts) | 111 GB | Very small | 112 GB | 112 GB | 112 GB | 113 GB | 114 GB | 115 GB | 119 GB |
The mmproj file for image input (F16) is 0.90 GB Measured . It is not included in the memory above, so add it if you use images.
Ollama ollama run hf.co/AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
llama.cpp llama-server -hf AtomicChat/Qwen3.8-Flash-Next-GGUF:Q4_K_M
Last checked: Nov 11, 2026
- Architecture
- qwen4exp
- llama.cpp b10660 and later
- Parameters
- 176.9B
- Max context length
- 262,144
- License
- qwen-community-1.0 Conditional
| Quantization | File size Measured | Quality guide | 4,096 | 8,192 | 16,384 | 32,768 | 65,536 | 131,072 | 262,144 max |
|---|---|---|---|---|---|---|---|---|---|
| Q2_K (2 parts) | 83.1 GB | Very large | 84.4 GB | 84.5 GB | 84.7 GB | 85.2 GB | 86.1 GB | 87.9 GB | 91.5 GB |
| IQ4_NL (2 parts) | 102 GB | Small | 103 GB | 103 GB | 104 GB | 104 GB | 105 GB | 107 GB | 110 GB |
| Q8_0 (2 parts) | 163 GB | Nearly identical | 164 GB | 164 GB | 164 GB | 165 GB | 166 GB | 167 GB | 171 GB |
The mmproj file for image input (Q8_0) is 0.62 GB Measured . It is not included in the memory above, so add it if you use images.
Ollama ollama run hf.co/ggml-org/Qwen3.8-Flash-Next-GGUF:Q2_K
llama.cpp llama-server -hf ggml-org/Qwen3.8-Flash-Next-GGUF:Q2_K
GGUF source
bartowski/Qwen3.8-Flash-Next-GGUF
Converted and published by a third party About this label
Last checked: Nov 11, 2026
- Architecture
- qwen4exp
- llama.cpp b10660 and later
- Parameters
- 176.9B
- Max context length
- 262,144
- License
- qwen-community-1.0 Conditional
| Quantization | File size Measured | Quality guide | 4,096 | 8,192 | 16,384 | 32,768 | 65,536 | 131,072 | 262,144 max |
|---|---|---|---|---|---|---|---|---|---|
| IQ1_S (2 parts) | 70.1 GB | Very large | 71.4 GB | 71.5 GB | 71.7 GB | 72.2 GB | 73.1 GB | 74.9 GB | 78.5 GB |
| IQ1_M (2 parts) | 72.0 GB | Very large | 73.3 GB | 73.4 GB | 73.6 GB | 74.1 GB | 75.0 GB | 76.8 GB | 80.4 GB |
| IQ2_XXS (2 parts) | 75.2 GB | Very large | 76.5 GB | 76.6 GB | 76.8 GB | 77.3 GB | 78.2 GB | 80.0 GB | 83.6 GB |
| IQ2_XS (2 parts) | 77.7 GB | Very large | 79.0 GB | 79.1 GB | 79.4 GB | 79.8 GB | 80.7 GB | 82.5 GB | 86.1 GB |
| IQ2_S (2 parts) | 77.8 GB | Very large | 79.1 GB | 79.2 GB | 79.4 GB | 79.9 GB | 80.8 GB | 82.6 GB | 86.2 GB |
| IQ2_M (3 parts) | 80.4 GB | Large | 81.6 GB | 81.8 GB | 82.0 GB | 82.4 GB | 83.3 GB | 85.2 GB | 88.8 GB |
| Q2_K (3 parts) | 80.9 GB | Very large | 82.2 GB | 82.3 GB | 82.5 GB | 83.0 GB | 83.9 GB | 85.7 GB | 89.3 GB |
| IQ3_XXS (3 parts) | 88.0 GB | Large | 89.3 GB | 89.4 GB | 89.6 GB | 90.1 GB | 91.0 GB | 92.8 GB | 96.4 GB |
| Q3_K_S (3 parts) | 89.4 GB | Large | 90.7 GB | 90.8 GB | 91.1 GB | 91.5 GB | 92.4 GB | 94.2 GB | 97.9 GB |
| IQ3_XS (3 parts) | 91.9 GB | Large | 93.2 GB | 93.3 GB | 93.6 GB | 94.0 GB | 94.9 GB | 96.7 GB | 100 GB |
| Q3_K_M (3 parts) | 92.0 GB | Medium | 93.2 GB | 93.3 GB | 93.6 GB | 94.0 GB | 94.9 GB | 96.7 GB | 100 GB |
| Q3_K_L (3 parts) | 93.2 GB | Medium | 94.5 GB | 94.6 GB | 94.8 GB | 95.3 GB | 96.2 GB | 98.0 GB | 102 GB |
| IQ3_M (3 parts) | 93.2 GB | Medium | 94.5 GB | 94.6 GB | 94.8 GB | 95.3 GB | 96.2 GB | 98.0 GB | 102 GB |
| IQ4_XS (3 parts) | 97.7 GB | Small | 99.0 GB | 99.1 GB | 99.3 GB | 99.8 GB | 101 GB | 102 GB | 106 GB |
| IQ4_NL (3 parts) | 100 GB | Small | 102 GB | 102 GB | 102 GB | 102 GB | 103 GB | 105 GB | 109 GB |
| Q4_0 (3 parts) | 101 GB | Medium | 102 GB | 102 GB | 102 GB | 103 GB | 104 GB | 105 GB | 109 GB |
| Q2_K_L (4 parts) | 107 GB | - | 108 GB | 109 GB | 109 GB | 109 GB | 110 GB | 112 GB | 116 GB |
| Q4_1 (3 parts) | 111 GB | Medium | 113 GB | 113 GB | 113 GB | 113 GB | 114 GB | 116 GB | 120 GB |
| Q4_K_S (3 parts) | 113 GB | Medium | 114 GB | 115 GB | 115 GB | 115 GB | 116 GB | 118 GB | 122 GB |
| Q3_K_XL (4 parts) | 119 GB | - | 121 GB | 121 GB | 121 GB | 121 GB | 122 GB | 124 GB | 128 GB |
| Q4_K_M (4 parts) | 120 GB | Small | 121 GB | 121 GB | 121 GB | 122 GB | 123 GB | 124 GB | 128 GB |
| Q5_K_S (4 parts) | 128 GB | Small | 129 GB | 129 GB | 130 GB | 130 GB | 131 GB | 133 GB | 137 GB |
| Q5_K_M (4 parts) | 135 GB | Very small | 136 GB | 136 GB | 136 GB | 137 GB | 138 GB | 139 GB | 143 GB |
| Q4_K_L (5 parts) | 139 GB | - | 141 GB | 141 GB | 141 GB | 141 GB | 142 GB | 144 GB | 148 GB |
| Q5_K_L (5 parts) | 151 GB | - | 152 GB | 152 GB | 153 GB | 153 GB | 154 GB | 156 GB | 159 GB |
| Q6_K (5 parts) | 168 GB | Very small | 169 GB | 170 GB | 170 GB | 170 GB | 171 GB | 173 GB | 177 GB |
| Q8_0 (6 parts) | 188 GB | Nearly identical | 190 GB | 190 GB | 190 GB | 190 GB | 191 GB | 193 GB | 197 GB |
| BF16 (9 parts) | 354 GB | Original precision | 355 GB | 355 GB | 356 GB | 356 GB | 357 GB | 359 GB | 362 GB |
The mmproj file for image input (F16) is 0.90 GB Measured . It is not included in the memory above, so add it if you use images.
Ollama ollama run hf.co/bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M
llama.cpp llama-server -hf bartowski/Qwen3.8-Flash-Next-GGUF:Q4_K_M
GGUF source
lmstudio-community/Qwen3.8-Flash-Next-GGUF
Converted and published by a third party About this label
Last checked: Sep 29, 2026
- Architecture
- qwen4exp
- llama.cpp b10660 and later
- Parameters
- 176.9B
- Max context length
- 262,144
- License
- qwen-community-1.0 Conditional
| Quantization | File size Measured | Quality guide | 4,096 | 8,192 | 16,384 | 32,768 | 65,536 | 131,072 | 262,144 max |
|---|---|---|---|---|---|---|---|---|---|
| Q4_K_M (3 parts) | 119 GB | Small | 120 GB | 121 GB | 121 GB | 121 GB | 122 GB | 124 GB | 128 GB |
| Q6_K (5 parts) | 168 GB | Very small | 169 GB | 169 GB | 169 GB | 170 GB | 171 GB | 172 GB | 176 GB |
| Q8_0 (6 parts) | 188 GB | Nearly identical | 190 GB | 190 GB | 190 GB | 190 GB | 191 GB | 193 GB | 197 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/lmstudio-community/Qwen3.8-Flash-Next-GGUF:Q4_K_M
llama.cpp llama-server -hf lmstudio-community/Qwen3.8-Flash-Next-GGUF:Q4_K_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. 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 UD-IQ1_S. To use another quantization, replace the name with one from the table above. Commands for files from other sources are in each source's section. How to run local LLMs
Ollama
Run it by pointing directly at the GGUF on Hugging Face.
ollama run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S
llama.cpp
Pass the repository and quantization name to llama-server (or llama-cli) with -hf.
llama-server -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S
LM Studio
Paste unsloth/Qwen3.8-Flash-Next-GGUF into the search box, download it, and choose the quantization from the file list.
Other models from Qwen
-
27.3B
Qwen
Qwen3.8-27B
- UD-Q4_K_M size
- 16.5 GB
- Memory at 8K
- 18.2 GB
Measured Estimated VRAM 24 GB+
-
8.2B
Qwen
Qwen3-VL-8B-Instruct
- Q4_K_M size
- 5.03 GB
- Memory at 8K
- 7.08 GB
Measured Estimated VRAM 8 GB+
-
9B
Qwen
Qwen3.5-9B
- Q4_K_M size
- 5.68 GB
- Memory at 8K
- 7.05 GB
Measured Estimated VRAM 8 GB+
-
34.7B
Qwen
Qwen3.6-35B-A3B
- UD-Q4_K_M size
- 22.1 GB
- Memory at 8K
- 23.4 GB
Measured Estimated VRAM 24 GB+
-
4.2B
Qwen
Qwen3.5-4B
- Q4_K_M size
- 2.74 GB
- Memory at 8K
- 4.11 GB
Measured Estimated VRAM 4 GB+
-
2B
Qwen
Qwen3-ASR-1.7B
- Q4_K_M size
- 1.32 GB
- Memory at 8K
- 3.11 GB
Measured Estimated VRAM 4 GB+
Models of a similar size (other developers)
-
176.9B
ISTA-DASLab
Qwen3.8-Flash-Next-GSQ-RCO
- Q2_0 size
- 66.4 GB
- Memory at 8K
- 67.8 GB
Measured Estimated VRAM 64 GB+
-
176.9B
SC117
Qwen3.8-Flash-Next-GSQ-RCO-abliterated
- Q2_0 size
- 66.8 GB
- Memory at 8K
- 68.2 GB
Measured Estimated VRAM 64 GB+
-
125.7B
agentionai
Qwen3.8-Flash-Next-Gyro
- TQ1_0 size
- 29.7 GB
- Memory at 8K
- 31.1 GB
Measured Estimated VRAM 32 GB+
-
125.7B
agentionai
Qwen3.8-Flash-Next-Gyro-abliterated-Huihui
- TQ1_0 size
- 29.7 GB
- Memory at 8K
- 31.1 GB
Measured Estimated VRAM 32 GB+
-
176.9B
ukisai
Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO
- Q2_0 size
- 66.5 GB
- Memory at 8K
- 67.9 GB
Measured Estimated VRAM 64 GB+
-
124.6B
ornith-ai
Ornith-1.5-122B
- Q4_K_M size
- 75.8 GB
- Memory at 8K
- 77.3 GB
Measured Estimated VRAM 96 GB+
Frequently asked questions
- How much memory do I need to run Qwen3.8-Flash-Next (UD-IQ1_S)?
- The file size is 66.4 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 67.8 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
- Can Qwen3.8-Flash-Next 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 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 with Ollama?
- Run "ollama run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.