Flint 40B A2.5B Abliterated — Hardware Requirements & GPU Compatibility
ChatCodeFunctions
Flint 40B A2.5B Abliterated is a 39.8B-parameter open language model from dima6312. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 24.27 GB of VRAM — see which GPUs and Macs can run it below.
Usable on a 24 GB GPU
Runs on 24 GB (Q4_1 · ~194 tok/s · 16K)Macs from 24 GB (Q2_K · ~65 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Flint 40B A2.5B Abliterated
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/dima6312/Flint-40B-A2.5B-abliterated-GGUF:Q4_K_MQ4_K_M · needs ~25.0 GB · 16K context
Download: Flint-40B-A2.5B-abliterated-Q4_K_M.gguf24.17 GBdima6312
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 32 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX PRO 4500 (32 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~177 tok/s
- generation speed
- Cost per 1M output tokens
- $0.53
- per 1M output tokens
How Much VRAM Does Flint 40B A2.5B Abliterated Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 17.3 GB | 18.9 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 128K context · ~219 tok/s | |
| 19.8 GB | 21.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 64K context · ~207 tok/s | |
| 21.8 GB | 23.3 GB | 4-bit · i-quant compact — Importance-weighted 4-bit, compact | Fits: 32K context · ~198 tok/s | |
| 22.8 GB | 24.3 GB | 4-bit · legacy+ — 4-bit legacy quantization with offset | Fits: 16K context · ~194 tok/s | |
| 24.3 GB | 25.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Does not fit: needs 25 GB | |
| 28.8 GB | 30.3 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 29.5 GB | |
| 33.2 GB | 34.8 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 34 GB | |
| 40.2 GB | 41.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 40.9 GB | |
| 80.0 GB | 81.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Does not fit: needs 80.7 GB |
Selected Q4_K_M
4-bit medium quantization25.0GBat 16K context
- Weights
- 23.9 GB
- KV cache
- 0.8 GB
- Overhead
- 0.3 GB
Doesn't fit RTX 4090 (reference) · needs 1.0 GB more, Q4_1 fits
≥50 tok/s needs ≥153 GB/s · RTX 5090 ~240, NVIDIA DGX Spark ~81
Or .
Which Hardware Can Run Flint 40B A2.5B Abliterated?
Q4_K_M · 24.3 GBFlint 40B A2.5B Abliterated (Q4_K_M) requires 24.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 32+ GB is recommended. Using the full 262K context window can add up to 13.1 GB, bringing total usage to 37.3 GB. 1 GPU can run it, including NVIDIA GeForce RTX 5090. 98 devices with unified memory can run Flint 40B A2.5B Abliterated, including NVIDIA DGX Spark, NVIDIA Jetson AGX Thor Developer Kit, Mac Studio M5 Max (36 GB).
20 GB
Q4_K_M · best fit Q2_K (18.0 GB)
1 GPU
RX 7900 XT~81Simulate output on RX 7900 XT32–40 GB
fits · 7.0 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 2 device families
RTX 5090~240Simulate output on RTX 5090M5 Max36 GB~66Simulate output on Mac Studio M5 Max (36 GB)M532 GB~39Simulate output on MacBook Air 13" M5 (32 GB)Orin~64Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~41Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
2| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Phi 3.5 MoE InstructMicrosoft | — | 23.9 GB | ~141 | same size |
| Falcon 40B InstructTII UAE | — | 23.8 GB | ~33 | same size |
Specifications
- Publisher
- dima6312
- Parameters
- 39.8B
- Active parameters
- 2.8B per token
- Architecture
- FlintForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 150,144
- Release Date
- 2026-10-23
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Flint 40B A2.5B Abliterated need?
Flint 40B A2.5B Abliterated requires 24.3 GB of VRAM at Q4_K_M, or 80.0 GB at BF16. Full 262K context adds up to 13.1 GB (37.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 39.8B × 4.8 bits ÷ 8 = 23.9 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 13.4 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Flint 40B A2.5B Abliterated?
Yes, at Q4_1 (22.8 GB) or lower. Higher quantizations like Q4_K_M (24.3 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Flint 40B A2.5B Abliterated?
For Flint 40B A2.5B Abliterated, Q4_K_M (24.3 GB) offers the best balance of quality and VRAM usage. Q5_K_M (28.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 17.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Flint 40B A2.5B Abliterated on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Flint 40B A2.5B Abliterated, the smallest at Q2_K. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 24.3 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run Flint 40B A2.5B Abliterated locally?
Yes — Flint 40B A2.5B Abliterated can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Flint 40B A2.5B Abliterated?
At Q4_K_M, Flint 40B A2.5B Abliterated can reach ~98 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 1.7 GB active ÷ (8000 × 0.65) = 0.33 ms, plus 49 layers × 0.055 ms = 2.69 ms, so 1000 ÷ 3.02 ms = ~331 tok/s
Estimated speed at Q4_K_M (24.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Flint 40B A2.5B Abliterated?
At Q4_K_M, the download is about 23.87 GB. The full-precision BF16 version is 79.57 GB. The smallest option (Q2_K) is 16.91 GB.
Which GPUs can run Flint 40B A2.5B Abliterated?
1 consumer GPU can run Flint 40B A2.5B Abliterated at Q4_K_M. Top options include NVIDIA GeForce RTX 5090.
Which devices can run Flint 40B A2.5B Abliterated?
98 devices with unified memory can run Flint 40B A2.5B Abliterated at Q4_K_M (24.3 GB), including ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB), GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.