EN
Book a call

Local AI · Recipe · 2× RTX 3090

GLM-5.3-Flash 320B UD-IQ3_XXS with llama.cpp on 2× RTX 3090

GLM-5.3-Flash 320B UD-IQ3_XXS with llama.cpp on 2× RTX 3090: 18.1 tok/s according to github.com (dataset as of Nov 3, 2026).

by noonghunna

18.1tok/sEveryday

1 request, prose prompt, no speculative decoding

Source: github.com
Intelligence (original model) · Artificial Analysis42with thinking

≤ 3 bit: quantization may cost quality

Instructions in the README Repo

Engine

Engine
llama.cpp
Quantization
GGUF UD-IQ3_XXS
Model family
GLM-5.3-Flash
Context
204,800
Parameters
320B MoE
Creator
noonghunna
GitHub stars
2,471
Repo updated
Nov 2, 2026

Measurements

Every sourced value of this recipe, each with its condition and source. Bars relative to the largest value in the group.

Decode · 1 request

  • Everyday (decode)18.1 tok/sNarrativ-Prompt (800-Wort-Essay), mean wall TPS; ub2048 Source 
  • Peak (decode)18.5 tok/sCode-Prompt (Quicksort), mean wall TPS; ub2048 Source 

Prefill by context

What you need

Hardware
2 × NVIDIA RTX 3090
Weights
Engine
llama.cpp
Context
204,800 tokens

Notes

What matters before you rebuild it.

  • ≤ 3 bit: quantization may cost qualityAt 3 bit and below the model may answer noticeably worse than the original. The intelligence number refers to the original.
  • Partly in system RAM
  • Incubating

Sources

Related recipes

4× DGX Spark

GLM-5.3-Flash NVFP4/MXFP8 CSF with SparkRing on 4× DGX Spark

by fujitsupolycom

68tok/sEveryday

1 request, generation at 32K context (speed table; measured only as a path of four Sparks inside a ring of eight, not as a ring of four), thinking always on (measured before the profile default high, i.e. template default max), with MTP3 (per recipe) Source 

Intelligence42with thinking
  • Custom kernel required
  • License unclear

NVFP4/MXFP8 CSF QAD (Local Inference Lab)vLLM (local-inference-lab Fork) via SparkRing (SIRCL-Collectives, switchless RDMA ueber ConnectX-7), Image Release 2026.10.2Weights Repo Updated Nov 2, 2026

Details
2× DGX Spark

GLM-5.3-Flash EXL3 with TensorFold on 2× DGX Spark (1M context, 4 streams)

by MiaAI-Lab

60.4tok/sEveryday

Prose decode, 1 request; quality (FP8 KV, 4-bit dense): GSM8K 98.8% / HumanEval 95.7% / HumanEval+ & MBPP+ 86.5% Source 

Intelligence42with thinking
  • ≤ 3 bit: quantization may cost quality
  • Custom kernel required
  • Non-commercial
  • License unclear

EXL3/TR3 4bpw routed experts + 4-bit dense, BF16 elsewhere, FP8 KVTensorFold v0.6.0 + Recipe v1.10 (README: 96 Patches; gepinntes Image v0.6.0-e66c657a433d mit 107 Patches: DFlash2+Copy-Drafts, 4-bit dense, FP8-KV, RoCE-One-Shot-All-Gather, Shared KV-Pool, optionaler Spill-Tier, Vision, Tool-Calling, Anthropic /v1/messages; PARALLEL=8 opt-in)Weights Repo Updated Oct 25, 2026

Details

← Back to overview

Local AI in your company?

In a workshop we work out which models and which hardware fit your tasks, and build the first agent on your infrastructure.

See the AI workshopBack to overview
Cookies

With your consent we use Google Analytics (Google, USA) and our own audience measurement to understand how our website is used. Strictly necessary storage, such as your cookie choice, happens without consent. You can change your choice at any time via “Cookie settings” in the footer. Privacy Policy · Cookie Policy