Arki05
Qwen3.8-27B-GGUF-shards
- Max context length
- 262,144
- Architecture
- qwen35
- License
- Commercial OK
- Base model
- Qwen/Qwen3.8-27B
- License
- apache-2.0
- llama.cpp
- b7990+
About Qwen3.8-27B-GGUF-shards
Qwen3.8-27B-GGUF-shards is a GGUF model based on Qwen/Qwen3.8-27B on Hugging Face. GGUF files are published by Arki05/Qwen3.8-27B-GGUF-shards. It has the qwen35 architecture, a maximum context length of 262,144 tokens (values written in the GGUF).
There are 24 quantizations, with file sizes from 5.77 GB (TQ1_0) to 29.0 GB (Q8_0) (actual sizes on Hugging Face).
Running TQ1_0 (5.77 GB) with an 8,192-token context needs an estimated 7.51 GB of memory, and an estimated 9.12 GB at 32,768 tokens. For 8,192 tokens, a GPU with 8 GB or more of VRAM (such as GeForce RTX 3070 Ti, Arc A580), or a Mac with 8 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 Apache License 2.0, which allows commercial use (keep the license text and copyright notice when redistributing). Check the original license for the terms of use.
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).
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
Last checked: Oct 17, 2026
- Architecture
- qwen35
- llama.cpp b7990 and later
- Max context length
- 262,144
- License
- apache-2.0 Commercial OK
Ollama ollama run hf.co/Arki05/Qwen3.8-27B-GGUF-shards:TQ1_0
llama.cpp llama-server -hf Arki05/Qwen3.8-27B-GGUF-shards:TQ1_0
Generation speed on common GPUs and Macs (estimated)
A rough guide to how fast TQ1_0 (5.77 GB) generates text. Each token reads the model weights once, so the upper limit is memory bandwidth ÷ file size. The guide is 60–80% of that, where most published measurements fall.
| Device | Memory bandwidth | Guide (tokens/s) Estimated | Upper limit |
|---|---|---|---|
| Arc A550M 8 GB | 224 GB/s | 23–31 | 39 |
| Radeon RX 6800 16 GB | 512 GB/s | 53–71 | 89 |
| GeForce RTX 5090 32 GB | 1,792 GB/s | 186–248 | 310 |
| Apple M2 16 GB | 100 GB/s | 10–14 | 17 |
| Apple M2 Pro 16 GB | 200 GB/s | 21–28 | 35 |
| Apple M5 Ultra 96 GB | 1,200 GB/s | 125–166 | 208 |
Estimates only. Prompt processing speed (limited by compute) is not included. Longer contexts and offloading part of the model to the CPU make it slower. Macs are shown only when installed memory is at least 4/3 of what is needed. Devices without published bandwidth (some GeForce cards, etc.) are not shown.
License and commercial use
Apache License 2.0 Commercial OK
Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files.
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 (qwen35) from b7990 (Feb 10, 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 TQ1_0. 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/Arki05/Qwen3.8-27B-GGUF-shards:TQ1_0
llama.cpp
Pass the repository and quantization name to llama-server (or llama-cli) with -hf.
llama-server -hf Arki05/Qwen3.8-27B-GGUF-shards:TQ1_0
LM Studio
Paste Arki05/Qwen3.8-27B-GGUF-shards into the search box, download it, and choose the quantization from the file list.
Other models from Arki05
Frequently asked questions
- How much memory do I need to run Qwen3.8-27B-GGUF-shards (TQ1_0)?
- The file size is 5.77 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 7.51 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
- Can Qwen3.8-27B-GGUF-shards be used commercially?
- The original model's license is Apache License 2.0 (Commercial use allowed).Allows commercial use, modification and redistribution. When redistributing, keep the license text and copyright notice, and note changes in modified files. Check the original license text before deciding.
- Does Qwen3.8-27B-GGUF-shards run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
- 8 GB: up to TQ1_0 (est. 7.51 GB); 12 GB: up to IQ2_S (est. 12.7 GB); 16 GB: up to Q4_K (est. 17.1 GB); 24 GB: up to Q6_K (est. 24.2 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
- What is the command to run Qwen3.8-27B-GGUF-shards with Ollama?
- Run "ollama run hf.co/Arki05/Qwen3.8-27B-GGUF-shards:TQ1_0" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.