Instructions to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-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 zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF # Run inference directly in the terminal: llama cli -hf zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF # Run inference directly in the terminal: llama cli -hf zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF # Run inference directly in the terminal: ./build/bin/llama cli -hf zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
Use Docker
docker model run hf.co/zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
- Llama new
- LM Studio
- Jan
- vLLM
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-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": "zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
- Ollama
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF with Ollama:
ollama run hf.co/zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
- Unsloth Desktop
- Pi
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
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": "zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF with Docker Model Runner:
docker model run hf.co/zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
- Lemonade
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
Run and chat with the model
lemonade run user.Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF-{{QUANT_TAG}}List all available models
lemonade list
- Hermes Agent
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-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 zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
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 zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
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 "zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF" \ --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"
Qwen3.8-Flash-Next IQ3_M GGUF (for a 24 GB GPU + 64 GB RAM PC) โ BETA
- 24G64G = for a PC with a 24 GB GPU (VRAM) + 64 GB RAM - a target setup, not a guarantee of speed.
- a mixed-type file - the experts are IQ3_S 57%, IQ4_NL 34%, Q8_0 7%, IQ4_XS 1% (by bytes), 3.94 bits a weight on average, about IQ3_M.
A GGUF of Qwen/Qwen3.8-Flash-Next made for one 24 GB GPU and 64 GB of RAM. Every expert is re-quantized with LDLQ from NVIDIA-format NVFP4 weights, in exactly unsloth UD-IQ4_XS's types and size (93.7 GB). All 512 experts are kept. Same size, same speed on the same emulated PC (69.9 vs 71.1 tok/s on coding tasks), and KL 0.068 vs 0.092 (-26%) against the NVFP4 model; KL on Japanese text 0.146 vs 0.195. Runs in Abyss and llama.cpp.
BETA: measured on one PC only (below). Reports from real 24 GB GPUs and other RAM sizes are very welcome (Community tab, or Abyss issues).
For a 16 GB GPU: Qwen3.8-Flash-Next-IQ3_M-16G64G-GGUF. For 12 GB + 32 GB: Qwen3.8-Flash-Next-E448-IQ2_M-12G32G-GGUF.
ๆฅๆฌ่ชใฎ่ชฌๆใฏไธใซใใใพใใ
Pick a size (this model's other repos)
| repo | for a PC with | download | note |
|---|---|---|---|
| Qwen3.8-Flash-Next-E448-IQ2_M-12G32G-GGUF | 12 GB GPU + 32 GB RAM | 67.5 GB | 448 of 512 experts kept |
| Qwen3.8-Flash-Next-IQ3_M-16G64G-GGUF | 16 GB GPU + 64 GB RAM | 86.9 GB | all 512 experts |
| this repo | 24 GB GPU + 64 GB RAM | 93.7 GB | all 512 experts, higher quality |
| Qwen3.8-Flash-Next-DGX-Spark-GGUF | DGX Spark (128 GB) | 86.9 GB | same files as 16G64G |
Earlier repo name: Qwen3.8-Flash-Next-24G64G-GGUF (old links redirect here).
Names: the quant in the repo name is the nearest llama.cpp type to the experts' average bits; most files mix several types (listed above), so they are not a stock quant of that name. E<n> = experts kept per layer (only when some were removed).
Compared with the same-size file
| download | resident (GPU + RAM) | KL (10 seqs) | same top token | KL, Japanese | KL, code | decode, 3 coding tasks | |
|---|---|---|---|---|---|---|---|
| this file | 93.7 GB | 64.2 GB | 0.068 | 90.3% | 0.146 | 0.092 | 69.9 tok/s |
| unsloth UD-IQ4_XS | 93.7 GB | 64.9 GB | 0.092 | 88.7% | 0.195 | 0.116 | 71.1 tok/s |
KL against the NVFP4 model (10 held-out sequences x 1,023 tokens: code, English, Chinese, Japanese and others), Abyss engine. "Resident" leaves out the 28.8 GB per-layer embedding table, which is read a few rows a token from the SSD. The two files have the same tensor types; only the rounding (LDLQ, calibrated with Japanese and chat turns) differs.
Real use
Abyss server, thinking on, two seeds, on the emulated PC (below):
| this file | unsloth UD-IQ4_XS | |
|---|---|---|
| Japanese (5 prompts: business email, explainer, summary, literature fact, arithmetic) | 10/10 answered, facts and sums right | 10/10 |
| 5 coding tasks with hidden tests | 5/5, 4/5 | 3/5, 5/5 |
| 8K-token prompt, find the needle | OK / OK | OK / OK |
| empty answers / prompt echoes | none | none |
| prompt processing (8K) | 1,680-1,689 tok/s | 1,670-1,683 tok/s |
Speed
Abyss v1.3.108, a 24 GB GPU + 64 GB RAM PC emulated on an RTX 5090 (32 GB): VRAM
capped at 24 GB (STRATA_GLM_VRAM_GB=24), RAM tier 46 GB inside a 58 GB cgroup, 8 CPU threads, iGPU off, NVMe SSD,
MTP drafter on.
- 3 coding tasks: 69.9 tok/s (unsloth UD-IQ4_XS 71.1)
- Japanese, 3 prompts: 61-77 tok/s
- llama.cpp, this file,
--n-cpu-moe 34(24.2 GB of VRAM): 26-34 tok/s
Abyss v1.3.108 or later is needed for the prompt path: the Q8_0 down experts of this layout read past their slot in older versions (also in unsloth's UD-IQ4_XS).
Other GPUs are not measured with this file. Reports welcome.
Files
Qwen3.8-Flash-Next-24G64G-0000N-of-00003.gguf, 3 shards; point your engine at -00001-of-00003.gguf. SHA256SUMS
in the repo. Experts: gate/up IQ3_S (layer 2 IQ4_XS), down IQ4_NL (layers 2, 4, 30, 46, 47 Q8_0). Non-expert tensors
(attention, router, shared expert, embeddings, per-layer embedding table) are unsloth UD-IQ4_XS's bytes, unchanged.
Feedback (this is a BETA)
- Speed on your PC:
./abyss.sh --bench --deepin Abyss, postabyss-bench.txtwith this issue form (change the title to your GPU), with your RAM size and SSD. - Quality in real use: empty answers, wrong language, loops, places where it is weaker than unsloth's file. A prompt that reproduces it helps most.
How it was made
With trench-gguf (tools/hessian_dump.cpp, tools/requant_experts.py,
tools/merge_experts.py):
- Hessians: the NVFP4 model (magnitudedev/Qwen3.8-Flash-Next-NVFP4-GGUF) over 1.26M tokens: its own chat turns (181 prompts: Japanese 44, Chinese 20, English 20, code 37, math 35, tool calls 25) followed by mixed text in the same languages and domains.
- LDLQ: every expert re-quantized from the NVFP4 weights (per-expert scales folded in) in UD-IQ4_XS's types, then merged into unsloth UD-IQ4_XS.
Running it
- Abyss v1.3.108 or later. Pack it once:
and start it withcd Abyss .venv/bin/python tools/iq_pack.py --fast --gguf /path/to/Qwen3.8-Flash-Next-24G64G-00001-of-00003.gguf --out /path/to/pack-fast--glm-pack /path/to/pack-fast(STRATA_GLM_RAM_GB=46on a 64 GB PC;STRATA_GLM_VRAM_GB=24on a larger card to test the 24 GB case). - llama.cpp (arch
qwen4exp, upstreamac8e1694dof 2026-10-29): runs as is. Checked withllama-server -m Qwen3.8-Flash-Next-24G64G-00001-of-00003.gguf -ngl 99 --n-cpu-moe 34 -c 32768 --jinja -t 8(24.2 GB of VRAM; use 35 or more on a real 24 GB card), the same real-use prompts: Japanese 5/5 answered (none empty), coding 3/5, the 8K needle found; decode 26-34 tok/s.
License
The original model's license (qwen-community-1.0). All credit for the model goes to the Qwen team; the NVFP4 weights the experts were made from are magnitudedev's, the non-expert tensors unsloth's.
ๆฅๆฌ่ช
- 24G64G = GPU๏ผVRAM๏ผ24 GB + RAM 64 GB ใฎ PC ๅใ๏ผๆณๅฎใใฆใใๆงๆใงใ้ใใไฟ่จผใใใใฎใงใฏใใใพใใ๏ผใ
- ๅฝขๅผใๆททใใใใกใคใซใงใใใจใญในใใผใใฏ IQ3_S 57%, IQ4_NL 34%, Q8_0 7%, IQ4_XS 1%๏ผๅฎน้ใฎๅฒๅ๏ผใๅนณๅ 3.94 ใใใใงใIQ3_M ใใใใงใใ
ใตใคใบใฎ้ธใณๆน๏ผๅใใขใใซใฎใปใใฎ็๏ผ
| ใชใใธใใช | ๅใใฎ PC | ใใฆใณใญใผใ | ใกใข |
|---|---|---|---|
| Qwen3.8-Flash-Next-E448-IQ2_M-12G32G-GGUF | GPU 12 GB + RAM 32 GB | 67.5 GB | ใจใญในใใผใ 512 ๅไธญ 448 ๅ |
| Qwen3.8-Flash-Next-IQ3_M-16G64G-GGUF | GPU 16 GB + RAM 64 GB | 86.9 GB | 512 ๅใในใฆ |
| ใใฎ็ | GPU 24 GB + RAM 64 GB | 93.7 GB | 512 ๅใในใฆใๅ่ณช้่ฆ |
| Qwen3.8-Flash-Next-DGX-Spark-GGUF | DGX Spark๏ผ128 GB๏ผ | 86.9 GB | 16G64G ใจๅใใใกใคใซ |
ไปฅๅใฎใชใใธใใชๅใฏ Qwen3.8-Flash-Next-24G64G-GGUF ใงใ๏ผๅคใ URL ใฏใใใธ่ปข้ใใใพใ๏ผใ
ๅๅใฎ้ๅญๅใฎๅใฏใใจใญในใใผใใฎๅนณๅใใใๆฐใซใใกใฐใ่ฟใ llama.cpp ใฎๅใงใใๅคใใฎใใกใคใซใฏ่คๆฐใฎๅใๆททใใฆใใใฎใง๏ผไธใซๅ
่จณ๏ผใใใฎๅๅใฎๆฎ้ใฎ้ๅญๅใจๅใใใฎใงใฏใใใพใใใE<ๆฐ> ใฏๅฑคใใจใซๆฎใใใจใญในใใผใใฎๆฐใงใ๏ผๆธใใใใจใใ ใไปใใพใ๏ผใ
Qwen/Qwen3.8-Flash-Next ใฎ GGUF ใใGPU 24 GB + RAM 64 GB ใฎ PC ๅใใซไฝใใพใใใ ใจใญในใใผใใฏใNVIDIA ๅฝขๅผใฎ NVFP4 ใฎ้ใฟใใ LDLQ ใง้ๅญๅใ็ดใใฆใใพใใๅใๅคงใใ๏ผ93.7 GB๏ผใ unsloth ใฎ UD-IQ4_XS ใจใพใฃใใๅใใงใใจใญในใใผใใฏ 512 ๅใในใฆๆฎใใฆใใพใใ ๅใ่จญๅฎใงๆฏในใใจใ้ใใฏๅใ๏ผใณใผใใฃใณใฐใฎ็ๆ 69.9 ใจ 71.1 tok/s๏ผใงใๅ ใฎ NVFP4 ใฎใขใใซใจใฎๅทฎ๏ผKL๏ผใฏ 0.092 โ 0.068๏ผ-26%๏ผใๆฅๆฌ่ชใฎๆ็ซ ใงใฏ 0.195 โ 0.146 ใงใใAbyss ใจ llama.cpp ใงๅใใพใใ
BETA ็ใงใใ ๆธฌใฃใใฎใฏไธใฎ 1 ๅฐใ ใใงใใๆฌ็ฉใฎ 24 GB ใฎ GPU ใใใปใใฎ RAM ๅฎน้ใงใฎ็ตๆใใCommunity ใฟใใ Abyss ใฎ issue ใงๆใใฆใใใใใจๅฉใใใพใใ
GPU 16 GB ๅใใฏ Qwen3.8-Flash-Next-IQ3_M-16G64G-GGUFใ GPU 12 GB + RAM 32 GB ๅใใฏ Qwen3.8-Flash-Next-E448-IQ2_M-12G32G-GGUF ใงใใ
ๅใๅคงใใใฎ็ใจใฎๆฏ่ผ
| ใใฆใณใญใผใ | ๅธธ้ง๏ผGPU + RAM๏ผ | KL๏ผ10 ๆฌ๏ผ | 1 ไฝใฎไธ่ด | ๆฅๆฌ่ชใฎ KL | ใณใผใใฎ KL | ็ๆ๏ผใณใผใใฃใณใฐ 3 ๅ๏ผ | |
|---|---|---|---|---|---|---|---|
| ใใฎ็ | 93.7 GB | 64.2 GB | 0.068 | 90.3% | 0.146 | 0.092 | 69.9 tok/s |
| unsloth UD-IQ4_XS | 93.7 GB | 64.9 GB | 0.092 | 88.7% | 0.195 | 0.116 | 71.1 tok/s |
KL ใฏ NVFP4 ใฎใขใใซใจใฎๅทฎใงใ๏ผ่ฉไพก็จใฎ 10 ๆฌ ร 1,023 ใใผใฏใณ๏ผใใๅธธ้งใใซใฏใๅฑคใใจใฎๅใ่พผใฟ่กจ๏ผ28.8 GBใ1 ใใผใฏใณใซใคใๆฐ่กใ ใ SSD ใใ่ชญใ๏ผใๅ ฅใใฆใใพใใใ2 ใคใฎ็ใฏใใณใฝใซใฎๅใๅใใงใ้ใใฎใฏไธธใๆน๏ผLDLQใๆฅๆฌ่ชใจใใฃใใใฎใใใจใใๅ ฅใใ่ชฟๆด๏ผใ ใใงใใ
ๅฎ้ใซไฝฟใฃใใจใใฎ็ตๆ
Abyss ใฎใตใผใใผใๆ่ใใใseed ใๅคใใฆ 2 ๅใไธใฎ่จญๅฎใงใใ
| ใใฎ็ | unsloth UD-IQ4_XS | |
|---|---|---|
| ๆฅๆฌ่ช 5 ๅ๏ผใใธใในใกใผใซใ่งฃ่ชฌใ่ฆ็ดใๆๅญฆใฎ็ฅ่ญใ่จ็ฎ๏ผ | 10/10 ๅ็ญใไบๅฎใจ่จ็ฎใฏๆญฃใใ | 10/10 |
| ใณใผใใฃใณใฐ 5 ๅ๏ผ้ ใใในใ๏ผ | 5/5ใ4/5 | 3/5ใ5/5 |
| 8K ใใผใฏใณใฎๆ็ซ ใใๆ ๅ ฑใๆขใ | ๆๅ / ๆๅ | ๆๅ / ๆๅ |
| ็ฉบใฎๅ็ญ / ใใญใณใใใฎ็นฐใ่ฟใ | ใชใ | ใชใ |
| ๅ ฅๅใฎๅฆ็๏ผ8K๏ผ | 1,680ใ1,689 tok/s | 1,670ใ1,683 tok/s |
้ๅบฆ
- RTX 5090๏ผ32 GB๏ผใงใGPU 24 GB + RAM 64 GB ใฎ PC ใ็ไผผใ่จญๅฎใงใใVRAM ใ 24 GB ใซๅถ้๏ผ
STRATA_GLM_VRAM_GB=24๏ผใRAM ใฎๆ 46 GB๏ผๅ จไฝ 58 GB ใซๅถ้๏ผใCPU 8 ในใฌใใใiGPU ใชใใNVMe SSDใMTP ใใฉใใฟใผใใใ - ใณใผใใฃใณใฐ 3 ๅ๏ผ69.9 tok/s๏ผunsloth UD-IQ4_XS ใฏ 71.1๏ผ
- ๆฅๆฌ่ช 3 ๅ๏ผ61ใ77 tok/s
- llama.cpp ใงใใฎ็ใ
--n-cpu-moe 34๏ผVRAM 24.2 GB๏ผ๏ผ26ใ34 tok/s - Abyss ใฏ v1.3.108 ไปฅ้ใๅฟ ่ฆใงใใใใฎไธฆใณใฎ Q8_0 ใฎ down ใจใญในใใผใใฏใใใใใๅใฎ็ใงใฏๅ ฅๅใฎๅฆ็ใง่ชญใฟ้ใใ่ตทใใฆใใพใใ๏ผunsloth ใฎ UD-IQ4_XS ใๅใใงใ๏ผใ
ไธญ่บซใปไฝใๆนใปๅใใๆน
- 3 ใใกใคใซใง 1 ใปใใใงใใ
-00001-of-00003.ggufใๆๅฎใใฆใใ ใใใSHA256SUMSใใใใพใใ - ใจใญในใใผใใฏ gate/up ใ IQ3_S๏ผๅฑค 2 ใ ใ IQ4_XS๏ผใdown ใ IQ4_NL๏ผๅฑค 2ใ4ใ30ใ46ใ47 ใฏ Q8_0๏ผใงใใใใไปฅๅค๏ผใขใใณใทใงใณใใซใผใฟใผใๅ ฑๆใจใญในใใผใใๅใ่พผใฟใๅฑคใใจใฎๅใ่พผใฟ่กจ๏ผใฏ unsloth UD-IQ4_XS ใฎใใฎใใใฎใพใพไฝฟใฃใฆใใพใใ
- ไฝใๆนใฏไธใฎ่ฑ่ชใฎ็ฏใฎใจใใใงใ๏ผtrench-ggufใNVFP4 ใฎใขใใซใซใใฃใใใฎใใใจใ 181 ๅ๏ผๆฅๆฌ่ช 44 ๅ๏ผใจๆ็ซ ใๆตใใฆๆธฌใฃใ 126 ไธใใผใฏใณๅใฎๆ ๅ ฑใง LDLQ๏ผใ
- Abyss v1.3.108 ไปฅ้ใงๅไฝใ็ขบ่ชใใฆใใพใ๏ผ64 GB ใฎ PC ใชใ
STRATA_GLM_RAM_GB=46๏ผใllama.cpp๏ผ2026-10-29 ใฎ ac8e1694d๏ผใงใใใฎใพใพๅใใพใใ--n-cpu-moe 34ใง VRAM 24.2 GB ใ ใฃใใฎใงใๆฌ็ฉใฎ 24 GB ใฎ GPU ใงใฏ 35 ไปฅไธใซใใฆใใ ใใใๅใๅฎ็จใในใใงใๆฅๆฌ่ช 5 ๅใในใฆใซๅ็ญ๏ผ็ฉบใฎๅ็ญใชใ๏ผใใณใผใใฃใณใฐ 3/5ใ8K ใฎๆ ๅ ฑๆขใใๆๅใใพใใใ
ใใฃใผใใใใฏใฎใ้กใ๏ผBETA ็๏ผ
- ใไฝฟใใฎ PC ใงใฎ้ใ๏ผAbyss ใง
./abyss.sh --bench --deepใๅฎ่กใใabyss-bench.txtใ ใใกใใฎ issue ใใฉใผใ ใซ่ฒผใฃใฆใใ ใใ๏ผใฟใคใใซใฎ GPU ๅใๆธใๆใใฆใใ ใใ๏ผใRAM ใฎๅฎน้ใจ SSD ใฎๆฉ็จฎใๆธใใฆใใใใใจๅฉใใใพใใ - ๅฎ้ใซไฝฟใฃใใจใใฎๅ่ณช๏ผ็ฉบใฎๅ็ญใ่จ่ชใฎๅใๆฟใใใ็นฐใ่ฟใใunsloth ใฎ็ใใๅผฑใใจๆใใใจใใใๅ็พใงใใใใญใณใใใใใใจไธ็ชๅฉใใใพใใ
- ใฉใคใปใณในใฏๅ ใฎใขใใซใจๅใใงใ๏ผqwen-community-1.0๏ผใ
- Downloads last month
- 60
We're not able to determine the quantization variants.
Model tree for zephel01/Qwen3.8-Flash-Next-IQ3_M-24G64G-GGUF
Base model
Qwen/Qwen3.8-Flash-Next