Instructions to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-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 julianmb/Qwen3.8-Flash-Next-IQ4_XS-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 julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

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 julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

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 julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

Use Docker

docker model run hf.co/julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

LM Studio
Jan

vLLM

How to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "julianmb/Qwen3.8-Flash-Next-IQ4_XS-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": "julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

Ollama
How to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF with Ollama:
```
ollama run hf.co/julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS
```
Unsloth Desktop

How to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

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": "julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF with Docker Model Runner:
```
docker model run hf.co/julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS
```

Lemonade

How to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.Qwen3.8-Flash-Next-IQ4_XS-GGUF-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-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 julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

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 julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS

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 "julianmb/Qwen3.8-Flash-Next-IQ4_XS-GGUF:IQ4_XS" \
  --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-IQ4_XS-GGUF / README.md

julianmb

Upload README.md with huggingface_hub

c9d10b0 verified 1 day ago

preview code

Raw

History Blame Contribute Delete

6.06 kB

metadata

license: other
license_name: qwen-community-license-1.0
base_model: Qwen/Qwen3.8-Flash-Next-FP8
library: gguf
quantized_by: julianmb
pipeline_tag: text-generation
tags:
  - qwen4exp
  - strix-halo
  - rocmfpx
  - gguf
  - ple-quantized

Qwen3.8-Flash-Next GGUFs — provenance-verified quants for Strix Halo

Four files:

file	size	what it is
`Qwen3.8-Flash-Next-IQ4_XS-PLE.gguf`	91 GiB	recommended daily driver — iq4_xs trunk with the 27G PLE n-gram table at iq4_nl
`Qwen3.8-Flash-Next-IQ4_XS.gguf`	116 GiB	static reference quant, PLE at q8_0
`Qwen3.8-Flash-Next-IQ4_XS-M2.gguf`	115 GiB	imatrix-calibrated quant, PLE table at q8_0 — best measured perplexity
`mtp-Qwen3.8-Flash-Next-Q8_0.gguf`	3.9 GiB	MTP draft sidecar for nathanw1014-lineage engines (fork-specific — will NOT load on apepojken/mainline)

M2 — the imatrix quant

second-generation quant: same trunk type (iq4_xs), but calibrated with a 926-entry imatrix (1,024 chunks) via the ROCmFPX banded quantizer, and the 51B PLE lookup table left at q8_0 (no --tensor-type cut). 5.56 bpw, 115 giB — 24 giB bigger than the 91g PLE file.

perplexity (wiki.test.raw, ctx 2048, 145 chunks):

quant	PPL
M2 (imatrix, PLE q8_0)	4.2809 ±0.025
PLE 91g	4.2932 ±0.025 (statistically tied, <0.5σ)
static 116g	4.5221 ±0.026 (~9σ worse)

speed profile is honest-mixed (single runs, nathanw1014 vulkan engine, q8_0 kv, temp 0):

depth	plain tg	mtp tg
8k	23.8 (≈ PLE 23.8)	25.1 (PLE 33.5 — M2 slower)
32k	19.0 (≈ PLE 19.0)	29.1 (best of the three)
128k	—	13.3 (PLE 13.5 — tied)

pick M2 when you want the best measured quality and don't mind the 24 giB: at ≤32k plain it matches PLE, and at 32k MTP it measured fastest. for shallow-depth MTP speed take the 91g PLE; for deep 128k+ MTP the static 116g had a small in-sweep edge (17.4 vs 13.3/13.5 — within the same-config spread, n=1 caveat).

provenance

every quant descends from an F16 that was byte-verified against the official Qwen/Qwen3.8-Flash-Next-FP8 checkpoint: hyper-connection norms folded to (1 + w) (97/97 tensors — the converter bug that produces deterministic garbage is fixed in our pipeline), PLE fp8 scale applied, expert stacking identity probed 512x3, GDN v-head reorder checked. details: https://github.com/julianmb/haloq38flash

the PLE cut (what makes the 91G special)

the 51B-parameter n-gram lookup table was moved from q8_0 (54G) to iq4_nl (27G) via --tensor-type. hash-gathered lookup rows tolerate the precision drop — verified by smoke and full benchmark, no degradation observed:

depth	static 116G plain/mtp t/s	PLE 91G plain/mtp t/s
0	29.2 / 48.4	29.9 / 53.1
8k	22.9 / 42.8	24.1 / 56.4
32k	19.5 / 29.5	20.1 / 30.2

prefill at 32k: 384 → 397 t/s. no collapse at depth. engine: nathanw1014 strix-halo-vulkan (ad914eb), vulkan/radv, q8_0 KV, -ub 2048, temp 0.

fork compatibility caveat (important)

the iq4_nl PLE rows assert in SOME forks: engines that feed gathered PLE rows directly as mul_mat B operands without dequantizing (apepojken qwen4exp-spec-mtp) abort at ggml-vulkan.cpp:7794 (b_type must be F32/F16/Q8_1). verified working on nathanw1014 strix-halo-vulkan. if your engine asserts on load or first token, use the 116G static file instead. M2 keeps the PLE table at q8_0 and has no such assert exposure.

provenance note

the same --tensor-type cut applied to unverified-source quants will NOT fix a broken converter (hc norms, PLE scale) — garbage in, garbage out. ours is built from a fixed, audited pipeline.

128k+ context caveat (measured)

the depth story is not monotonic. measured on the same engine (nathanw1014 vulkan, q8_0 kv, temp 0, single runs):

depth	static 116g plain/mtp t/s	PLE 91g plain/mtp t/s
0	29.2 / 48.4	29.9 / 53.1
8k	22.9 / 42.8	24.1 / 56.4
32k	19.5 / 29.5	20.1 / 30.2
128k	10.8 / 26.9	11.0 / 18.6

plain decode collapses with depth on both quants (~11 t/s at 128k) — the cost is context-mechanics (sparse-attention indexer), not the quant.
with mtp at 128k the PLE quant measured SLOWER than static (18.6 vs 26.9, single runs): plausible draft-acceptance drop from ple quantization noise compounding over deep n-gram history. unverified mechanism, n=1 caveat.
practical: <=32k work → PLE file. 128k+ contexts → static file (or M2 for the best quality at plain speed).

run it (strix halo, 128 GB unified memory)

full methodology, receipts, and the benchmark record: https://github.com/julianmb/haloq38flash

docker (one-liner; image default serves the 91g PLE on :8080):

git clone https://github.com/julianmb/haloq38flash && cd haloq38flash
docker compose up --build

point it at M2 with the MTP sidecar and the warm-turn cache:

docker compose run qwen38-flash-next /app/llama-server \
  -m /models/Qwen3.8-Flash-Next-IQ4_XS-M2.gguf \
  -md /models/mtp-Qwen3.8-Flash-Next-Q8_0.gguf \
  --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.75 \
  --cache-ram 8192 --ctx-checkpoints 32 \
  -c 32768 -ngl 999 -fa on -ctk q8_0 -ctv q8_0 -ub 2048 -t 4

or raw llama.cpp (nathanw1014 strix-halo-vulkan lineage engines):

llama-server -m Qwen3.8-Flash-Next-IQ4_XS-M2.gguf \
  -md mtp-Qwen3.8-Flash-Next-Q8_0.gguf \
  --spec-type draft-mtp --spec-draft-n-max 6 --spec-draft-p-min 0.75 \
  -ngl 999 -fa on -ctk q8_0 -ctv q8_0 -ub 2048 -t 4 -c 32768

perf notes: -t 16 lifts prefill up to +43% at 128k (decode indifferent); the --cache-ram/--ctx-checkpoints warm-turn flags make repeated context nearly free (measured 438 s → 0.68 s at 128k, 994 s → 0.74 s at 256k — 640x/1351x). swap M2's filename for the other quants; same flags.

license

qwen community license 1.0 (distribution permitted with notice; maas restrictions apply). base model: Qwen/Qwen3.8-Flash-Next.