Lfm2.5 2.6B Fable5 Coding Agent Heretic — Hardware Requirements & GPU Compatibility
ChatFunctions
Lfm2.5 2.6B Fable5 Coding Agent Heretic is a 2.7B-parameter open language model from saidutta69 in the LFM2.5 family. It supports a context window of up to 131,072 tokens. At Q4_K_M it needs about 2.04 GB of VRAM — see which GPUs and Macs can run it below.
9.0K downloads
7 likesSpecifications
- Publisher
- saidutta69
- Family
- LFM2.5
- Parameters
- 2.7B
- Architecture
- Lfm2ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 128,000
- Release Date
- 2026-08-19
- License
- Other
Get Started
How Much VRAM Does Lfm2.5 2.6B Fable5 Coding Agent Heretic Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.6 GB | 9.5 GB | 1.15 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.6 GB | 9.5 GB | 1.18 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.7 GB | 9.7 GB | 1.31 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 1.8 GB | 9.7 GB | 1.35 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 2.0 GB | 10.0 GB | 1.62 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.4 GB | 10.3 GB | 1.92 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 2.6 GB | 10.6 GB | 2.23 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.1 GB | 11.1 GB | 2.70 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Lfm2.5 2.6B Fable5 Coding Agent Heretic?
Q4_K_M · 2.0 GBLfm2.5 2.6B Fable5 Coding Agent Heretic (Q4_K_M) requires 2.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. Using the full 131K context window can add up to 7.9 GB, bringing total usage to 10.0 GB. 50 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Lfm2.5 2.6B Fable5 Coding Agent Heretic?
Q4_K_M · 2.0 GB59 devices with unified memory can run Lfm2.5 2.6B Fable5 Coding Agent Heretic, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Lfm2.5 2.6B Fable5 Coding Agent Heretic need?
Lfm2.5 2.6B Fable5 Coding Agent Heretic requires 2.0 GB of VRAM at Q4_K_M, or 5.8 GB at BF16. Full 131K context adds up to 7.9 GB (10.0 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.7B × 4.8 bits ÷ 8 = 1.6 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 8.4 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M2.0 GBQ4_K_M + full context10.0 GB- What's the best quantization for Lfm2.5 2.6B Fable5 Coding Agent Heretic?
For Lfm2.5 2.6B Fable5 Coding Agent Heretic, Q4_K_M (2.0 GB) offers the best balance of quality and VRAM usage. Q5_K_S (2.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.6 GB.
VRAM requirement by quantization
Q2_K1.6 GBQ4_01.8 GBQ4_K_S1.9 GBQ4_K_M ★2.0 GBQ5_K_M2.4 GBBF165.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Lfm2.5 2.6B Fable5 Coding Agent Heretic on a Mac?
Lfm2.5 2.6B Fable5 Coding Agent Heretic requires at least 1.6 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Lfm2.5 2.6B Fable5 Coding Agent Heretic locally?
Yes — Lfm2.5 2.6B Fable5 Coding Agent Heretic can run locally on consumer hardware. At Q4_K_M quantization it needs 2.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Lfm2.5 2.6B Fable5 Coding Agent Heretic?
At Q4_K_M, Lfm2.5 2.6B Fable5 Coding Agent Heretic can reach ~2353 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~321 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.0 × 0.65 = ~2549 tok/s
Estimated speed at Q4_K_M (2.0 GB)
~2549 tok/s~321 tok/s~2549 tok/s~2353 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Lfm2.5 2.6B Fable5 Coding Agent Heretic?
At Q4_K_M, the download is about 1.62 GB. The full-precision BF16 version is 5.39 GB. The smallest option (Q2_K) is 1.15 GB.
- Which GPUs can run Lfm2.5 2.6B Fable5 Coding Agent Heretic?
50 consumer GPUs can run Lfm2.5 2.6B Fable5 Coding Agent Heretic at Q4_K_M (2.0 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 50 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Lfm2.5 2.6B Fable5 Coding Agent Heretic?
59 devices with unified memory can run Lfm2.5 2.6B Fable5 Coding Agent Heretic at Q4_K_M (2.0 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.